Research map / 3D vision / Face and shape
Local Implicit Grid Representations for 3D Scenes
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 |
|---|---|---|---|
| Use local part representations rather than a single global object representation | ShapeNet autoencoding trained on chairs · Unseen object categories | F-Score: 0.274 -> 0.692 | Helped |
| Represent scenes with local implicit grids rather than one global implicit network | Matterport scene representation · Matterport scenes | F-Score: 0.647 -> 0.985 | Helped |
| Reconstruct with Local Implicit Grids instead of PSR10 | Scene reconstruction · Matterport, 100 points/$m^2$ | F-Score: 0.455 -> 0.889 | Helped |
| Reconstruct with Local Implicit Grids instead of PSR10 | Scene reconstruction · SceneNet, 20 points/$m^2$ | F-Score: 0.317 -> 0.859 | Helped |
| Add overlapping latent grids (ablation) | LIG with 50cm parts and latent code length 32 · SceneNet, 100 points/$m^2$ | F-Score: 0.857 -> 0.957 | Helped |
| Use 25cm rather than 50cm parts (ablation) | LIG · SceneNet, 100 points/$m^2$ | F-Score: 0.957 -> 0.921 | Hurt |
| Use 75cm rather than 50cm parts (ablation) | LIG · SceneNet, 100 points/$m^2$ | F-Score: 0.957 -> 0.929 | Hurt |
| Reduce latent code length from 32 to 8 (ablation) | LIG · SceneNet, 100 points/$m^2$ | F-Score: 0.957 -> 0.879 | Hurt |
Closest papers by meaning
- Local Deep Implicit Functions for 3D Shape (CVPR 2020 · similarity 0.90)
- Learning to Infer Implicit Surfaces without 3D Supervision (NeurIPS 2019 · similarity 0.90)
- 3DILG: Irregular Latent Grids for 3D Generative Modeling (NeurIPS 2022 · similarity 0.89)
- OctField: Hierarchical Implicit Functions for 3D Modeling (NeurIPS 2021 · similarity 0.89)
- Learning Implicit Fields for Generative Shape Modeling (CVPR 2019 · similarity 0.89)
- ARO-Net: Learning Implicit Fields From Anchored Radial Observations (CVPR 2023 · similarity 0.88)
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.