Research map / 3D vision / NeRF and radiance fields
ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
Zhongtao Wang, Jiaqi Dai, Qingtian Zhu, Yilong Li, Mai Su, Fei Zhu, Meng Gai, Shaorong Wang, Chengwei Pan, Yisong Chen, Guoping Wang
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 local and global period-varying features (ablation) | ChronoGS · ChronoScene Lawncourt | PSNR: 18.18 -> 22.16 | Improved |
| add period-invariant base feature (ablation) | ChronoGS · ChronoScene Canteen | PSNR: 24.57 -> 25.15 | Improved |
| add local period-varying feature (ablation) | ChronoGS · ChronoScene Lawncourt | PSNR: 21.96 -> 22.16 | Improved |
| add global period-varying feature (ablation) | ChronoGS · ChronoScene Canteen | PSNR: 24.94 -> 25.15 | Improved |
| jointly train all periods in unified scaffold vs per-period Scaffold-GS | ChronoGS · Overstreet | PSNR: 21.87 -> 22.66 | Improved |
| joint multi-period training reduces iterations vs per-period static | ChronoGS · Overstreet | training iterations: 120k -> 40k | Improved |
| ChronoGS vs static 3DGS on real scenes | ChronoGS · ChronoScene real | PSNR: 18.29 -> 22.16 | Improved |
| ChronoGS vs GS-W on synthetic scenes | ChronoGS · ChronoScene synthetic | PSNR: 25.11 -> 28.80 | Improved |
| anchor-based Scaffold-GS trained on mixed periods vs 3DGS | Scaffold-GS · ChronoScene real | PSNR: 18.29 -> 16.27 | Hurt |
| use ChronoGS memory vs smallest baselines | ChronoGS · ChronoScene real | memory: 0.52GB vs 0.18GB (4DGS) | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Scaffold-GS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 2024) · better on 2 of 2 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
- Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments (CVPR 2024 · similarity 0.86)
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.85)
- STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor Scenes (ICLR 2025 · similarity 0.84)
- The STVchrono Dataset: Towards Continuous Change Recognition in Time (CVPR 2024 · similarity 0.84)
- ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation (NeurIPS 2024 · similarity 0.84)
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos (NeurIPS 2025 · similarity 0.84)
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.
