GenCAD

https://gencad.github.io/

by dagenix • 2 months ago

441 127 2 months ago

gencad.github.io

knollimar• 2 months ago

It says "can convert cad latents into a sequence of parametric CAD commands"

Which CAD program? I'm confused

Am I reading this right?

Most importantly, GenCAD does not merely generate a 3D solid but also the entire CAD program.

lagrange77• 2 months ago

Which CAD program?

Doesn't matter. CAD models/objects are represented by a sequence of operations on a primitive or sketch. Unlike meshes, that describe the manifested resulting shape of objects in 3D programs like Blender.

So it's about the fact, that their model outputs that hierarchy of operations. The history of development, not just the result.

SchemaLoad2• 2 months ago

How does it not matter? Every CAD program is not going to have exactly the same interface and commands. I doubt for example this will for example generate and OpenSCAD text file.

itishappy• 2 months ago

Nothing stops you from storing a history of mesh operations. This is exactly what modifiers (including geometry nodes) do in Blender today.

dbcurtis• 2 months ago

Which CAD program? I'm confused

Clue here: > Our proposed GenCAD architecture...

So, at this point, it seems like this will work with all CAD programs, since they have yet to encounter any systems that they can't work with. More seriously, my guess would be whatever one is available for free in their lab. Kind of standard operating procedure for academic projects -- do a proof of concept, make a video that avoids known bugs, get a grade, push source to git, graduate. Good ideas come out of that... production code... eh... maybe.

More likely someone ends up in the situation that my kid did, previous graduate student's git repo is stale by 2 versions of C++, and 4 versions of ROS, and neither of the two unit tests still work after porting.

hug• 2 months ago

It's DeepCAD* output, it looks like, which is a JSON payload that is the sketch / extrude / whatever steps, which is itself based on Onshape output.

Looks like you can go JSON -> step files, but not really in such a way that you can modify any of the operations.

* https://github.com/mightyhorst/DeepCAD

mamami• 2 months ago

Ideally it would tie in with an llm, no? Like you would want to be able to say something like "create a design of car suspension subject to x,y,z contrains"

cush• 2 months ago

The input is images, and the output is CAD models, so it appears you could use a multi-modal LLM to natural language -> image -> CAD

simpleintheory2• 2 months ago

Is this Google-affiliated? The heading font is Product/Google Sans which IIRC only Alphabet is allowed to use and the entire webpage seems to be Google-style but neither of the two named researchers seem to be employed by Google?

vpzom• 2 months ago

Per https://fonts.google.com/specimen/Google+Sans/license

"These fonts are licensed under the Open Font License. You can use them in your products & projects – print or digital, commercial or otherwise."

simpleintheory2• 2 months ago

Yeah, TIL, turns out they changed the license: it used to be under https://fonts.google.com/license/productsans

ironhaven• 2 months ago

A another take on this problem is zoo.dev . They wrote a brand new from scratch cad engine that is driven a custom openscad style language called kcl.

Then then have a trained llm that has can generate kcl to either create new parts or act as a llm assistant for changes to existing parts.

It’s neat that llms can do 3-D but I wonder how much of the problem is integration.

cjtrowbridge• 2 months ago

This has been easy with OpenSCAD for a long time. I have made lots of cool, complex models this way. I built a repo of the prompts I use to show the llm how to do this and it includes many of the models I've created this way...

https://github.com/cjtrowbridge/vibe-modeling

jvanderbot2• 2 months ago

Same. Working with an LLM and OpenSCAD has been totally painless.

richk449• 2 months ago

I’ve been using cadquery and build123 with Claude code and I find it incredibly painful.

What is your workflow for llm integration to openscad?

oasisaimlessly• 2 months ago

OpenSCAD has almost zero crossover with B-rep modelling ('true' CAD, what this apparently is), though.

iamgopal2• 2 months ago

how hard it is ? with AI prevalent, how long ? any pointers to start from ?

twelvechairs• 2 months ago

OpenSCAD uses CSG which is generally better. Easy to convert CSG to BREP. Cant generally do the opposite

Karliss3• 2 months ago

This isn't B-rep based modelling. Far from it. It builds up the feature tree and then uses geometry kernel to generate B-rep based representation. The final generator output script could probably be adjusted to generate openscad. It only supports 2d drawings containing lines, arcs and circles and extrude operation for making them 3d. Operations like fillets and chamfers which depend on intermediate B-rep model state are not supported.

I would even argue that for basic modelling majority of tools/features in CAD operate at the abstraction closer to CSG for describing what and B-rep is only treated as how. Just like good chunk of code based CAD use combination of CSG for what and triangle mesh based geometry engine for how. That's assuming you consider standard 2d->3d operations (extrude, revolve, sweep along arbitrary 2d profile) as valid primitives for CSG.

User comes into direct contact of B-rep in very specific situations: 1 doing operations like fillets/chamfers/draft/thickness based on intermediate geometry, 2 attaching sketches or other features to generated geometry or using generated edges (instead of new sketches) for guiding operations like complex sweeps, 3 surface based modelling workflows where you build up the the solid from individual faces typically including complex curved surfaces.

In case of 1 and 2 the the dependency on b-rep based representation is only marginal, in theory you could select edges in triangle mesh based underlying representation but the final result but quality of result wouldn't be as nice and TNP issues for parametric model editing would likely be even bigger than it is for existing CAD. That's not really CSG territory anymore but isn't exclusive to B-rep either, and involves a bunch of work that's outside the scope of B-rep. In non parametric mesh modellers with more destructive editing workflows like blender chamfers and fillets work fine. And if anything for reliable parametric models you often want to limit dependencies on intermediate geometry as that depends on CAD keeping track of where each edge/face originated from outside the b-rep and increases the chance of TNP issues.

3 is critical for industrial design containing large amount of complex curved surfaces like cars and other consumer products, but there are also many more technical parts where it can be completely ignored. Cad tutorials for beginner tutorials almost completely ignore this category of cad modelling. The part about not being exclusive to b-rep also applies for surface modelling part.

alexgoodhart• 2 months ago

What is the inference overhead on this

q3k2• 2 months ago

I'm sorry, but which ones of these are complex? I'm looking through some [1] [2] [3] of the output PNGs and they look trivial. Like, my first 3d model in Blender trivial.

In comparison, here's one of my recent designs: what I would still call a very simple case [4]. And it's not like I'm a trained mechanical engineer working commercially, this is stuff I design in my spare time as a programmer.

[1] https://github.com/cjtrowbridge/vibe-modeling/blob/main/outp...

[2] https://github.com/cjtrowbridge/vibe-modeling/blob/main/outp...

[3] https://github.com/cjtrowbridge/vibe-modeling/blob/main/outp...

[4] https://object.ceph-eu.hswaw.net/q3k-personal/fe3e54e6df604a...

ugh123• 2 months ago

The examples they show are so basic.

dyauspitr3• 2 months ago

Yeah they’re basically a single extrude of the sketch

ecto5• 2 months ago

Readers may also enjoy my open source Rust BRep CAD kernel https://github.com/ecto/vcad or the hosted version at https://vcad.io.

I also wrote a bit about what goes into CAD apps! https://campedersen.com/tessellation

ecto5• 2 months ago

(forgot to mention, it's wired up to Claude so you can vibe CAD, like OP but with a few more steps - I'd like to train a similar model soon! I also wrote about my first stab at this https://campedersen.com/cad0)

vincent-uden• 2 months ago

Seeing as I'm attempting to build my own CAD program in Rust I checked out the hosted website. I'm not really sure what is supposed to be working and what isn't.

I can't help but to be skeptical of one person writing ~115k LOC in 4 months which is just the Rust crates, nevermind the frontend (which is another 100k LOC!!!).

I'm curious why you decided to go with "eager" tessellation. Creating a circle immediately results in a bunch of lines which resemble a circle but would fail under tangency constraints quickly. Is this a current limitation or part of the strategy for the kernel?

clmul• 2 months ago

As someone also working on CAD in their spare time, also tried the hosted app. I get the feeling that this is made by someone who has never opened a (professional) CAD app at all. It feels like a mix between a tool like blender and CSG-style CAD, but even all of that doesn't seem to work. Maybe this is the proof that vibe coding does not work, at least not for this kind of application.

In my own project I use LLMs very sparingly and hesitantly, but made the observation that they are not very useful on the hard parts of CAD. I expect this is because of a lack of training material. Most professional CAD applications are proprietary and books on the topic are usually sparse on implementation details. The non-BRep CAD applications such as OpenSCAD and family are probably overrepresented in the training data.

This might also explain why people's experiences with LLMs are very varied. If you stay in the happy path of CRUD web development and stuff all is nice and well, but if you start to veer off this path you get more and more challenged.

throwup2382• 2 months ago

I'm curious why you decided to go with "eager" tessellation. Creating a circle immediately results in a bunch of lines which resemble a circle but would fail under tangency constraints quickly. Is this a current limitation or part of the strategy for the kernel?

I’ve seen several vibe coded attempts at a geometric kernel (including several of my own) and this happens every time.

Vibe coding a geometric kernel is practically impossible because sooner or later* the LLM inevitably takes the tessellation shortcut and if you don’t catch it, the codebase is completely compromised. At the end of the day, there isn’t enough training data in architecture or algorithms (opencascade solvespace and truck being the only real examples, all significantly worse than commercial kernels like Parasolid or ACIS).

* usually as soon as you ask it to do anything non-trivial. If you’re lucky you’ll get a naive Newton marching algorithm on analytical bodies, which is slightly better but has the same problem with degenerate and pathological cases (coincidence, tangents, parallels)

ecto5• 2 months ago

Tessellation is simply required to render the IR. The viewport is guiding the cursor to the vertices (perhaps a bug) but the engine is not forcing their use. I also built a ray caster :)

What wasn't working? I would love real feedback -

geuis3• 2 months ago

To the author if they happen to see this. Please kill the auto playing video. If someone is listening to something else on their phone this always takes over and interrupts.

whatsupdog• 2 months ago

TIL: people are still browsing the internet without an ad blocker.

cassianoleal• 2 months ago

Doesn’t even have to go that far. TIL people are still browsing the internet without disabling auto-play on their browsers.

dyauspitr3• 2 months ago

How do you use an actually effective ad blocker on the iPhone?

achllle• 2 months ago

I wanted to see how well it performed on real pictures of parts or hand-drawn drawings, but when I tried setting up the docker image, immediately ran into all kinds of dependencies not being installed. The examples make me suspect it doesn't work well beyond images that were generated from CAD in the first place.

atoav• 2 months ago

If only there was some kind of container that allowed you to bundle all your dependencies together with your software.

dnnddidiej2• 2 months ago

That thing is called Nix

xiaoyu2006• 2 months ago

docker image, immediately ran into all kinds of dependencies not being installed

Ironically the former is engineered to avoid the latter.

pocksuppet• 2 months ago

A Docker image is a reinvention of a program, and a Docker container is a reinvention of a process. At first they were self-contained - but so were the first programs and processes.

Riany• 2 months ago

the idea is good, but the examples still feel like a distance to handle real constraints and dimensions

nik282000• 2 months ago

Website renders so poorly on my phone that I cant read half the text. Fits the bill for a slop project.

isaisabella• 2 months ago

The demo seems pretty cool, but also pretty simple. When it comes to complicate models, I afriad it would be hard to generate the accurate 3D model.

clippy99• 2 months ago

Maybe I missed something, if you have the image rendering in the first place, you already (likely) have the CAD. It is a nice demo, but what is the utility?

soupspaces2• 2 months ago

generate from sketch or replicate a part you don't have

andrew_kwak• 2 months ago

Checked out GenCAD. It seems pretty useful for simple circuit designs. Wondering if it supports import/export with other CAD formats?

jrflo• 2 months ago

Neat, but I don't really see the utility. The time consuming part of CAD drawing comes from figuring out the correct dimensions of each feature, spacing, sizing, tolerances, etc., and constraining the drawing in a way so that it's easy to tweak later on- which this doesn't do at all. Maybe you could draw a 2d sketch of what you want then generate it, but you'd still have to do the hard part.

nextlevelwizard4• 2 months ago

If down the line this model could create 3D model from 2D images that would be very neat way to pay less for war gaming models

semi-extrinsic• 2 months ago

You can already do this with apps like Kira. I believe it is especially good on the iPhone variants with LiDAR.

protocolture2• 2 months ago

Already done. Cults generally has stls of 40k models before release. Its just a matter of finding them.

satvikpendem• 2 months ago

Gaussian splats and neural radiance fields already exist.

CodeCompost• 2 months ago

Missing IKEA screws.

timvdalen• 2 months ago

IKEA will send you those for free if you order them on the site, including free shipping

smartmic• 2 months ago

As is often the case in the GenAI space, this also appears to be a solution to a non-existent problem.

willis9362• 2 months ago

I very much have this problem. I am uninterested in the art of sketching and constraining. I have spent many hours attempting and am content with the knowledge that I don't have the touch but still sometimes have problems I want to solve with 3D prints. LLMs could offer a solution, but they are bullshit machines and by their nature over promise. Drafting is not a trivial skill that we just wave a wand and magically have it automated. We'll get there eventually, but we're not there.

stck• 2 months ago

If you can just take a pencil and draw a piece of furniture, press a button and get a semi-decent CAD drawing to tweak, that'd be a huge tool for carpenters and such.

Arch-TK• 2 months ago

"to tweak" is probably quite far away even if "get a semi-decent CAD drawing" was remotely reliable which it isn't.

VLM• 2 months ago

This is a classic outside the field vs inside the field conceptual disagreement.

From the outside, the hard part of designing a chair is making a blueprint. At least making a blueprint looks hard to people who've never made one. According to outsiders, the next layer of the onion is perhaps inserting reasonable constraint dimensions for similar reasons.

From the inside, as a guy who's recreationally made furniture, the hard part is judgment about joint selection and design, experience with wood warping (all wood changes shape with the seasons, a good woodworker makes it look easy to work around and a bad one makes expensive firewood that rapidly falls apart). Another insider PoV is judgment about wood selection to get the correct balance of final finish durability and appearance. Finally working toward outer layers of the onion, its time to do parametric joint design decisions... What's the ideal number and size of dovetail joints for, perhaps, a drawer.

I've seen prints of chairs before I don't need a LLM to make one similar to the ones I've seen before and could probably make from memory (at least ones I built myself), the library has loanable books and woodworking magazines. I do see the attraction from the outside.

Consider something like a Windsor chair. The larger the wedge in the spindles the tighter and longer lasting the chair until you break something trying to force them in; there's a lot of judgment and experience in designing, selecting, and installing spindles, but none of it is written down so it'll be hard to train a LLM... Tighten it until it breaks then don't tighten it that much next time. Most super detailed plans for Windsors are for inferior machine produced replicas which are not necessarily useful for a fine woodworker and are not exactly what craftsmen would aspire to. People who want "a cheap chair" will buy a 4-pak of folding chairs from walmart anyway, not make a homemade Windsor-style chair.

Another somewhat more blunt example is for actual woodworkers the "problem" with hand cut dovetails isn't knowing what they look like or how to make a diagram of one, but gaining the experience behind a hammer and chisel to push your luck while cutting them as far as possible without going too far and turning the part into scrap. One unavoidable part of woodworking is I've turned quite a bit of wood into scrap on the last step; oh well make another. At least I can burn scrap wood to keep warm LOL.

Its kind of like from outside the programming fraternity the non-programmers think the only skills required to program are typing real fast and being very experienced at fizzbuzz during interviews. But that doesn't work IRL, from an inside-out perspective.....

The woodworking world is not exactly lacking for a library of "semi-decent" plans. An automated system to make enormous quantities of low quality unverified and untested plans would not really help the field, no.

whazor• 2 months ago

Strangely, it would work better if it generates CAD as code with clear labels. Then you can grab your caliper and make sure its all the right size.

KaiserPro• 2 months ago

Good question!

So why $work-1 spent so much time on this was quite logical. When you have point clouds generated from crappy head mounted cameras, you get models that are very complex.

for example, if you look at a point cloud of an Ikea LACK (https://www.ikea.com/gb/en/p/lack-nest-of-tables-set-of-2-wh...) It will be massively complex. this means that when you want to perform nay kind of interaction with it, its computationally difficult (https://www.researchgate.net/publication/221064696/figure/fi...)

So an active area of research is point cloud to "CAD" model (ie simplyfied, where a LACK tabl would be ~40 triangles rather than 400k)

One of those ways is to say "oh this pointcloud looks like a table, lets generate a bunch of hypothesis tables and see if they fit." One way to do that is to have a model that understands parametric CAD, and can create a number of tables with parameters that can be adjusted until it fits.

A perhaps easier way is to take a point cloud, get an image model trained on CAD models to draw models, in 2d imagery, then use something like this to get an actual model out.

Its not efficient, but it might work.

There are also lots of other cases, like automatic plagiarism, which are less good.

johnvanommen2• 2 months ago

If you wanted to brute force it, it might be possible to have it generate a hundred outputs and then include a second pass to automatically select the generated model that most accurately resembles the expected output.

Basically leverage the randomness to create many variations, then select the most accurate variation automatically.

Terribly wasteful of time and processing power, but so is using GPU time to make pretty pictures randomly.

ololobus2• 2 months ago

I think this is true under assumption that you know the CAD tool well. From my recent experience (I have a 3D printer), I regularly find myself in a situation where I know what I want to do, I can do measurements and I can make a sketch on a paper. Yet, making it a proper 3D model in something like FreeCAD is super tedious. I know OpenSCAD relatively well, but when it comes to something more complex I struggle a lot. The recent example, I was making a water tap for Lego duplo kitchen sink for my little one :)

So I would really appreciate a good AI/LLM tool that I can feed my sketch and parameters and it can save me hours of searching web and watching tutorials on how to extrude a circle over a curve

BTW, any existing AI tools work really well with OpenSCAD, so if you want a parametrized model that can be made out of simple shapes, I highly recommend this flow

johnvanommen2• 2 months ago

So I would really appreciate a good AI/LLM tool that I can feed my sketch and parameters and it can save me hours of searching web and watching tutorials on how to extrude a circle over a curve

I think this is possible, but the ‘trick’ would be translating your instructions in English into some kind of language that the CAD software understands.

I’m on a bunch of 3D printing forums, and everyone tries to describe what the finished product would LOOK like. They end up making PICTURES when what they really want is a STL file.

Two dimensions are easier to visualize then three, so let’s put it this way:

If you wanted to turn “English” into “a 2D image that’s dimensionally accurate”, you’d want to translate from “English” to “SVG.”

SVG is dimensionally accurate. JPG isn’t. The file format itself has no concept of “dimensions” only “pixels.”

mk_stjames• 2 months ago

Your comment on how you feel trying to execute a model is similar to the inverse of how many Mechanical Engineers (used to) talk about coding - they know what they want, they can write down what they want a program to do, they just don't know what to type out in a programming language or how to compile the code or use the IDE, etc etc.

There are mechanical engineers out there who can literally model objects nearly as fast and they can 'think' about the layout of said object. If you look at the complexity of, say, a CAD model from a real, highly complex aluminum casting section of an automotive subframe, or the living-room-sized cross-fuselage spar forging of a fighter aircraft, with hundreds of ribs and fillets and features- and compare that to the simple model you are trying to make in OpenSCAD, you should quickly realize the parallels in difficulty you are trying to express (similar to the person without knowledge of C++ or Python watching someone be able to build applications by typing code from their fingertips as if they already knew what to type...)

You are struggling for a few reasons- 1., it is a knowledge hurdle of an entire field you are trying to surmount- again, go watch someone actually model a real, complex part and watch the speed, they can do so in a tool like Solidworks, CATIA, NX, etc... at a rate that is far different because they have experience that it can honestly take even good people years to accumulate - and 2. they are using professional tools - you mention OpenSCAD, like it is CAD, but it isn't. It is programmatic mesh generation, and it turns out that programmatically typing out how to generate complex things is much more difficult than a combination of a graphical GUI and graph-based generator that all big CAD programs figured out starting in the 1980s. If those tools you use were really the best way to make complex models 'paramaterized', then why do we design our fighter jets, Formula 1 cars, or Space X rockets in Dassault's CATIA or Siemen's NX ?

You want a LLM to take a sketch to your CAD, but what I'm saying is, there are people out there that can skip the sketch and build the CAD as fast as you can likely hand draw the first sketch, and these are skills you can actually learn, but you may just be using the wrong tools and have not had the practice necessary.

gwbas1c• 2 months ago

I've resorted to using Rust + vcad, although I think I'll give OpenSCAD a spin.

I haven't tried telling AI to "make a thing," but I'm able to get Co-pilot to refactor code. It's just the geometry that makes my head spin.

andyfilms12• 2 months ago

If you use something like OnShape or Fusion, you could easily get comfortable enough to model those parts in about a day. Once get the hang of it, you'll be amazed how fast you can work.

It will take much longer than a day for AI to get to this level, so there's not much to lose by just learning how to use the software now :)

hadlock• 2 months ago

I've been having excellent success with prompts like "use cadquery and build x" for moderately simple stuff, like bearing clearance gauge for 3d prints. I don't like openscad because while it will technically produce .step , they don't import "clean" into fusion, etc the way step files produced by cadquery do

Karliss3• 2 months ago

Even if you are completely skeptical about the AI cad model generation they also demonstrated their representation for model search/matching. Having a smarter search method for cad models based on 3d geometry in addition to traditional text search would be nice to have.

zkmon• 2 months ago

How are the input images generated?

hspeiser2• 2 months ago

I spent a few hours trying to get this to work, and I couldn’t get it to produce usable results on anything except the training data, even with very simple drawings.

I noticed in the GitHub that they mention it is only around 60% reliable even on their own training data, but the image shown on the front page feels pretty misleading. I made 10 images that were very similar in complexity to the examples shown, and even after running it around 50 times on each image, not a single one worked correctly. In the rare cases where it produced something, the output was completely wrong.

This seems pretty misleading in its current state and definitely needs more work.

ololobus2• 2 months ago

I’m also confused by their examples. All of them seem to be perfect renders/exports from 3D models — this is not the use case where I see it the most useful. Making a parametrized CAD model out of a hand-drawn sketch — yes, please

galangalalgol• 2 months ago

I have tried getting claude to generate openscad for sketches it does poorly. But that would be great

Karliss3• 2 months ago

When skimming a research paper in addition to abstract don't forget to read "limitations and future work" and "conclusions".

In the limitation section they are quite direct with it: "images used .. are mostly isometric and noise-free CAD-images" and "limited CAD vocabulary used in this study needs to be extended by including more sophisticated CAD tokens such as revolve operation, edge operation (e.g., fillets/chamfers)". It currently supports only series of pads (can be subtractive). Many simple beginner exercises of seemingly similar complexity don't fit those constraints. Some of the parts shown could be more naturally created using wider set of tools, but technically can be created using only pads.

So even if you tried with clean screenshot of simple 3d model, it will likely fail if camera settings aren't right, and it will fail if model can't be represented using series of pad operations. Anything containing spheres, cones, nearly all lathe parts, fillets which can't be included in 2d sketches will fail. In theory arbitrary extrusion angles are supported, but all examples showed only axis aligned parts.

That said I wouldn't be surprised if it failed even if you considered exact limitations not just similar complexity in your attempts.

Assuming images in the googledrive are the training data, "mostly isometric and noise-free CAD images" is a bit of understatement. All of them are at very specific angles using and single style. Specific solid gray infill color for "images", and white infill with weird shading around perimeter for "sketches". Both with white background and pixelated non antialised 1px lines. No reason to expect it capable of processing anything which doesn't have exactly same visual style. For practical product that would have to be solved but that wasn't really the point of this research. All the style transference papers have show that it's more or less solvable problem, but for a paper exploring what model architecture and 3d representation could work best for AI cad it seems like unnecessary distraction that would only bloat the training costs and time. Most annoying part is that it makes hard to test the model with your own inputs.

hspeiser2• 2 months ago

Took isometric screenshots of drawings from very simple parts I made in onshape and imported them. They were black and white and very clear.

Lapsa4• 2 months ago

"In 1975, Dr. Joseph Sharp proved that correct modulation of microwave energy can result in wireless and receiverless transmission of audible speech."

dang3• 2 months ago

Can you please stop posting about this issue? You've unfortunately been doing it excessively, including many repetitive comments. That's not a good use of HN.

I don't mean to come across as personally critical. From your comments it sounds possible (I am not sure, of course) that you have been having some distressing experiences. If so, we hope things improve. But please don't post these comments to HN - they aren't on topic here, and they're not an effective way to address the situation.

Lapsa4• 2 months ago

what would you presume would be an effective way to address the situation? have tried just about everything

Lapsa4• 2 months ago

if you don't think it's a serious issue - would like to tell you that I currently have nothing to eat

physicsguy2• 2 months ago

This is over a year old now, why post now? There have been other advancements in this area.

john_minsk• 2 months ago

Could you please share?

physicsguy2• 2 months ago

For e.g.:

https://arxiv.org/abs/2603.04337 https://arxiv.org/abs/2603.05607 https://arxiv.org/abs/2605.01171

For a more detailed review: https://github.com/lichengzhanguom/LLMs-CAD-Survey-Taxonomy

dajt• 2 months ago

I'm stumped by things like this. The drawing & modelling are not the difficult bit - the CAM programming is.

That seems difficult enough that I have not found an open source program to load a 3D model and allow me to set the toolpaths in a UI, never mind have an LLM generate them from the model.

regularfry• 2 months ago

That's a completely different difficult problem, and totally dependent on the manufacturing process. CNC? Sure. FDM from the same .step? Almost entirely irrelevant, that's the slicer's job. SLA? Doesn't make sense to ask the question.

throwup2382• 2 months ago

The drawing & modelling are not the difficult bit - the CAM programming is.

Actually the drawing and modeling are very much the hard part, so much so that the open source geometric kernels are decades behind the commercial ones. The computational geometry is genuinely a hard problem due to floating point errors and degenerate cases like parallel surfaces and tangent lines.

Once you have the geometric kernels, CAM is little more than a physically aware pathfinding optimization problem. Computationally expensive but otherwise straight forward. The kernel, on the other hand, has to be built up experimentally, tracking down every place where the math breaks down or there’s a pathological case, until you’ve got the thousands of special cases worked out.

ricardobayes• 2 months ago

Anyone finding this interesting will likely also like OpenSCAD - generate 3D CAD models from code. https://openscad.org/

ponyous• 2 months ago

I've seen this and other attempts like this[0] while exploring improvements for my CAD AI[1]. And I think these are potentially powerful solutions, but none of the current projects/weights have enough training (data or time) to make it work on arbitrary models. MeshCoder pretty much works only on models based of their training data. I haven't tried GenCAD but other commenters have confirmed my suspicion.

[0] https://daibingquan.github.io/MeshCoder/

[1] https://grandpacad.com

soupspaces2• 2 months ago

Wait. Could this be used for videos keeping consistencies across frames?

https://youtube.com/@thang010146

nancyminusone• 2 months ago

If you can get this to read dimensions and apply constraints, you've done it. But that doesn't look like the case.

Every time I see one of these things,its like whoever worked on it doesn't know how to use CAD or understand what CAD is used for.

rirze• 2 months ago

This.

Every 6 months, I reevaluate how well LLMs can model from scratch or can modify existing files.

It's very superficial (atleast the last time I tried it). I'm guessing if/when LLMs crack visual reasoning, they might be able to do it.

eMPee584• 2 months ago

Well visual reasoning is one approach, another is a coding-like approach like this cadquery-based solution https://articraft3d.github.io/ which was also posted here a couple of days ago.. https://news.ycombinator.com/item?id=48153064 Curious what you (and others) think, they also are collecting a pool of examples including prompt, reasoning log and token cost, quite interesting imho.

iamgopal2• 2 months ago

There should be "login with gemini" or "login with claude" for saas world.

GenCAD

Related Stories