Research map / 3D vision / Depth and stereo
ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction
Yanzhe Liang, Ruijie Zhu, Hanzhi Chang, Zhuoyuan Li, Jiahao Lu, Tianzhu Zhang
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 ReFlow (initialization, separation, self-correction flow matching) to 4DGS | 4DGS · NVIDIA Monocular mean | PSNR: 25.81 -> 28.20 | Improved |
| use ReFlow instead of MoDec-GS | MoDec-GS · NVIDIA Monocular per-scene SSIM | SSIM: Balloon2 0.909 -> 0.908; Jumping 0.858 -> 0.855; mean 0.879 -> 0.903 | Mixed |
| add ReFlow to 4DGS | 4DGS · HyperNeRF | PSNR: 25.16 -> 26.15 | Improved |
| add self-correction flow matching to baseline (ablation) | 4DGS baseline · NVIDIA Monocular | PSNR: 25.81 -> 26.45 | Improved |
| add raw unaligned point cloud initialization (ablation) | 4DGS baseline · NVIDIA Monocular | PSNR: 25.81 -> 24.50 | Hurt |
| add hierarchical aligned canonical space initialization (ablation) | 4DGS baseline · NVIDIA Monocular | PSNR: 25.81 -> 26.60 | Improved |
| add static-dynamic separation (ablation) | aligned init · NVIDIA Monocular | PSNR: 26.60 -> 27.00 | Improved |
| add Full Flow Matching (ablation) | init + separation · NVIDIA Monocular | PSNR: 27.00 -> 27.85 | Improved |
| add Camera Flow Matching (ablation) | init + separation + Full FM · NVIDIA Monocular | PSNR: 27.85 -> 28.20 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MoDec-GS — MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting (CVPR 2025) · better on 5 of 5 shared results
- MotionGS — MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 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
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.88)
- ReMatching Dynamic Reconstruction Flow (ICLR 2025 · similarity 0.87)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.87)
- HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene (NeurIPS 2025 · similarity 0.87)
- DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement (CVPR 2024 · similarity 0.87)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · 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.
