Aurelien Lucchi, Dario Pavllo, Graham Spinks, Thomas Hofmann, Marie-Francine Moens
We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| dariopavllo/convmesh | canonical | 2 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| divide_pred | Ran | dariopavllo/convmesh/run_generation.py code served (permissive licence) · get_code("86fe15b439328f16") |
| mean_iou | Ran | dariopavllo/convmesh/run_reconstruction.py code served (permissive licence) · get_code("a3ccb1025ca05d3e") |
| to_grid | Not yet run | dariopavllo/convmesh/run_reconstruction.py code served (permissive licence) · get_code("bd0faab0cfcf45a0") |
| to_grid_tex | Not yet run | dariopavllo/convmesh/run_generation.py code served (permissive licence) · get_code("7ab31145bc29a65d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control over generated objects as well as the possible applications of such models. In this work, we bridge this gap by leveraging recent advances in differentiable rendering. We design a framework that can generate triangle meshes and associated high-resolution texture maps, using only 2D supervision from singleview natural images. A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN. We demonstrate the efficacy of our method on Pascal3D+ Cars and CUB, both in an unconditional setting and in settings where the model is conditioned on class labels, attributes, and text. Finally, we propose an evaluation methodology that assesses the mesh and texture quality separately.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.07660")
get_code_for_paper("2006.07660")
have("2006.07660")
Connect an agent — have() is free.