Research map / 3D vision / NeRF and radiance fields
LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation
Archana Swaminathan, Anubhav Gupta, Kamal Gupta, Shishira R Maiya, Vatsal Agarwal, Abhinav Shrivastava
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add latent manifold loss and depth/occlusion regularizers to vanilla latent interpolation (ablation) | LEIA · PartNet-Mobility average | PSNR: 27.81 -> 29.55 | Improved |
| add latent manifold loss (ablation) | LEIA · PartNet-Mobility | PSNR: 28.54 -> 29.40 | Improved |
| add depth smoothness regularization (ablation) | LEIA · PartNet-Mobility | PSNR: 26.93 -> 29.63 | Improved |
| add occlusion regularization (ablation) | LEIA · PartNet-Mobility | PSNR: 28.64 -> 29.64 | Improved |
| add positional encoding to the latent (ablation) | LEIA · PartNet-Mobility | PSNR: 28.48 -> 27.11 | Hurt |
| train with 4 states instead of 2 (ablation) | LEIA · PartNet-Mobility | PSNR: 28.04 -> 29.69 | Improved |
| LEIA versus PARIS on multi-part objects | LEIA · Storage2 (multi-part) | PSNR: 26.35 -> 31.07 | Improved |
| LEIA versus PARIS on single-part objects | LEIA · Storage1 (single-part) | PSNR: 28.66 -> 26.69 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PARIS — PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects (ICCV 2023) · better on 3 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BANMo: Building Animatable 3D Neural Models From Many Casual Videos (CVPR 2022 · similarity 0.89)
- D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021 · similarity 0.89)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.88)
- Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling (CVPR 2024 · similarity 0.88)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.88)
- TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene (NeurIPS 2024 · 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.
