Research map / 3D vision / Face and shape
Learning Implicit Fields for Generative Shape Modeling
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace the CNN-AE decoder with the implicit field decoder in latent-GAN shape generation | 3D shape generation on ShapeNet · ShapeNet 3D generation, Average | COV-LFD (%): 72.99 -> 73.36 | Helped |
| replace the CNN-AE decoder with the implicit field decoder in latent-GAN shape generation | 3D shape generation on ShapeNet · ShapeNet 3D generation, Average | MMD-LFD: 2,892 -> 2,831 | Helped |
| replace the CNN decoder with the implicit decoder | MNIST CNN-GAN · MNIST 2D shape generation | MMD-CD: 0.155 -> 0.151 | Helped |
| replace the WGAN decoder with the implicit decoder | MNIST WGAN · MNIST 2D shape generation | MMD-CD: 0.158 -> 0.149 | Helped |
| replace the WGAN decoder with the implicit decoder | MNIST WGAN · MNIST 2D shape generation | COV-CD (%): 86.5 -> 84.7 | Hurt |
| use the implicit decoder rather than a CNN decoder | MNIST shape generation · MNIST 2D shape generation | COV-CD (%): 82.7 -> 75.2 | Hurt |
| use the implicit decoder rather than a CNN decoder | MNIST shape generation · MNIST 2D shape generation | IS: 8.79 -> 9.36 | Helped |
| use the implicit decoder for image-to-shape reconstruction | single-view 3D reconstruction · ShapeNet SVR, Rifle | LFD: 6,507 -> 5,067 | Helped |
| use the implicit decoder for image-to-shape reconstruction | single-view 3D reconstruction · ShapeNet SVR, Table | LFD: 2,725 -> 2,918 | Hurt |
| sample the implicit field at 256³ rather than 64³ (ablation) | IM-AE · ShapeNet autoencoding, Table | LFD: 2,370 -> 2,201 | Helped |
| sample the implicit field at 256³ rather than 64³ (ablation) | IM-AE · ShapeNet autoencoding, Table | CD: 12.05 -> 11.54 | Helped |
| use a CNN decoder instead of the implicit decoder | 3D shape autoencoding · ShapeNet autoencoding, Chair | IoU: 74.22 -> 65.65 | Hurt |
Closest papers by meaning
- Learning to Infer Implicit Surfaces without 3D Supervision (NeurIPS 2019 · similarity 0.89)
- Local Implicit Grid Representations for 3D Scenes (CVPR 2020 · similarity 0.89)
- ARO-Net: Learning Implicit Fields From Anchored Radial Observations (CVPR 2023 · similarity 0.88)
- ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion (CVPR 2025 · similarity 0.86)
- Make-A-Shape: a Ten-Million-scale 3D Shape Model (ICML 2024 · similarity 0.86)
- Enhancing Implicit Shape Generators Using Topological Regularizations (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.