Research map / 3D vision / NeRF and radiance fields
Neural Scene Chronology
Haotong Lin, Qianqian Wang, Ruojin Cai, Sida Peng, Hadar Averbuch-Elor, Xiaowei Zhou, Noah Snavely
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 |
|---|---|---|---|
| Use step function encoding for time instead of unencoded time (ablation) | Neural Scene Chronology · 5Pointz | PSNR: 18.07 -> 19.19 | Improved |
| Use step function encoding for time instead of unencoded time (ablation) | Neural Scene Chronology · 5Pointz | SSIM: 0.678 -> 0.715 | Improved |
| Use step function encoding for time instead of unencoded time (ablation) | Neural Scene Chronology · 5Pointz | LPIPS: 0.345 -> 0.307 | Improved |
| Add appearance parametric encoding (ablation) | Neural Scene Chronology · 5Pointz | PSNR: 19.48 -> 21.32 | Improved |
| Add appearance parametric encoding (ablation) | Neural Scene Chronology · 5Pointz | SSIM: 0.612 -> 0.745 | Improved |
| Add appearance parametric encoding (ablation) | Neural Scene Chronology · 5Pointz | LPIPS: 0.423 -> 0.274 | Improved |
| Allow dynamic geometry rather than assume static geometry (ablation) | Neural Scene Chronology · 5Pointz | PSNR: 21.32 -> 20.82 | Hurt |
| Use step function encoding with dimension 16 rather than positional encoding frequency 5 (ablation) | Neural Scene Chronology · 5Pointz | PSNR: 20.71 -> 21.32 | Improved |
| Increase step function encoding dimension from 16 to 24 (ablation) | Neural Scene Chronology · 5Pointz | entropy: 2.213 -> 2.625 | Hurt |
| Add time input to NeRF-W | NeRF-W · Times Square, Akihabara, 5Pointz, The Met | PSNR: 16.59 -> 18.71; 17.41 -> 19.16; 17.52 -> 19.41; 23.21 -> 23.83 | Improved |
| Use step function encoding and the proposed scene representation rather than time-conditioned NeRF-W | NeRF-W-T · Times Square, Akihabara, 5Pointz, The Met | entropy: 4.990 -> 3.122; 5.483 -> 2.482; 5.768 -> 2.213; 4.923 -> 2.399 | Improved |
Closest papers by meaning
- ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes (CVPR 2026 · similarity 0.87)
- Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling (CVPR 2024 · similarity 0.87)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.87)
- S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes (CVPR 2024 · similarity 0.86)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.86)
- EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision (ICLR 2024 · similarity 0.85)
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.
