Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
Authors: Kunal Gupta, Manmohan Chandraker
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments demonstrate that NMF faciliates several applications such as single-view mesh reconstruction, global shape parameterization, texture mapping, shape deformation and correspondence. We show quantitative comparisons to prior works and more importantly, compare resulting meshes on physically meaningful tasks such as rendering, simulation and 3D printing to highlight the importance of manifoldness. In this section we show qualitative and quantitative results on the task of auto-encoding and single view reconstruction of 3D shapes with comparison against several state of the art baselines. |
| Researcher Affiliation | Academia | Kunal Gupta Manmohan Chandraker University of California, San Diego {k5gupta, mkchandraker}@eng.ucsd.edu |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code and data are released.1 1https://kunalmgupta.github.io/projects/Neural Meshflow.html and try our colab notebook. |
| Open Datasets | Yes | Data We evaluate our approach on the Shape Net Core dataset [52], which consists of 3D models across 13 object categories which are preprocessed with [53] to obtain manifold meshes. |
| Dataset Splits | Yes | We use the training, validation and testing splits provided by [6] to be comparable to other baselines. |
| Hardware Specification | Yes | on 5 NVIDIA 2080Ti GPUs for 2 days. |
| Software Dependencies | No | The paper mentions software like PyTorch3D and Blender but does not provide specific version numbers for these or other ancillary software components. |
| Experiment Setup | Yes | During training, the NODE is solved with a tolerance of 1e 5 and interval of integration set to t = 0.2 for deforming an icosphere with 622 vertices. We train NMF for 125 epochs using Adam [50] optimizer with a learning rate of 10 5, weight decay of 0.95 after every 250 iterations and a batch size of 250, on 5 NVIDIA 2080Ti GPUs for 2 days. For single view reconstruction, we train an image to point cloud predictor network with pretrained Res Net [51] encoder of latent code 1000 and a fully-connected decoder with size 1000,1000,3072 with relu non-linearities. The point predictor is trained for 125 epochs on the same split as NMF auto-encoder. |