Clément Jambon
clementjambon.bsky.social
Clément Jambon
@clementjambon.bsky.social
PhD student at MIT💻 I love Computer Graphics🎨 Previously at SNU, ETH Zurich, Nvidia, Inria and École polytechnique🔙 I run, cycle and 🍻 during my free time.
To showcase these capabilities, we've implemented and made available an interactive viewer.
Check out our code at github.com/brepdiff/bre...
Interactive results are also available on our webpage! brepdiff.github.io/interactive/...
8/8
June 30, 2025 at 2:42 PM
More interestingly, we show that by leveraging DDIM inversion, we can interpolate between B-reps, even when their topologies differ. We believe these capabilities represent a significant step toward enhancing traditional design workflows with generative modeling.
7/8
June 30, 2025 at 2:42 PM
The explicitness of the masked UV grid representation enables users to freely manipulate geometry without being constrained by topological validity. This supports intuitive and advanced editing operations such as autocompletion and merging B-reps.
6/8
June 30, 2025 at 2:42 PM
Masked UV grids are directly compatible with diffusion transformers. In the paper, we introduce a modified noise schedule and an asynchronous denoising strategy to more effectively learn the underlying distribution, achieving performance on par with existing multi-stage models.
5/8
June 30, 2025 at 2:42 PM
We instead propose a single-stage generative model for B-reps. Our key insight is that the full topology can be inferred from the faces alone by representing each face as a masked UV grid defined by structured point samples of its surface.
4/8
June 30, 2025 at 2:42 PM
The boundary representation (B-rep) is the predominant format for 3D models in CAD applications.
However, its highly irregular and complex structure presents significant challenges for generative modeling, often necessitating intricate multi-stage generation pipelines.
3/8
June 30, 2025 at 2:42 PM
BrepDiff generates boundary representations (B-reps) with diffusion. Here, we show examples of denoising trajectories along with their post-processed CAD solids.
2/8
June 30, 2025 at 2:42 PM
📢 I'm excited to share BrepDiff, our single-stage B-rep diffusion model, which enables unconditional generation and editing of B-reps.
This work will be presented at #SIGGRAPH2025 with @mingilikesmangos.bsky.social, @dongsuzhang.bsky.social, and Young Min Kim.
🌐: brepdiff.github.io
1/8
June 30, 2025 at 2:36 PM