Research map / 3D vision / Gaussian splatting
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
Chenguo Lin, Yuchen Lin, Panwang Pan, Yifan Yu, Tao Hu, Honglei Yan, Katerina Fragkiadaki, Yadong Mu
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 camera token (ablation) | MoVieS (static pretraining) · RealEstate10K | PSNR: 25.56 -> 26.81 | Improved |
| add Plucker embedding alone (ablation) | MoVieS (static pretraining) · RealEstate10K | PSNR: 25.56 -> 25.81 | No clear effect |
| add Plucker embedding on top of camera token (ablation) | MoVieS (static pretraining) · RealEstate10K | PSNR: 26.81 -> 27.60 | Improved |
| add point-wise L1 motion supervision (ablation) | MoVieS · Aria Digital Twin | EPE_3D: 0.7938 -> 0.2262 | Improved |
| add distribution loss alone (ablation) | MoVieS · Aria Digital Twin | EPE_3D: 0.7938 -> 0.2496 | Improved |
| add distribution loss on top of point-wise L1 (ablation) | MoVieS · Aria Digital Twin | EPE_3D: 0.2262 -> 0.2153 | Improved |
| add explicit motion supervision to NVS-only training (ablation) | MoVieS · DyCheck | mPSNR: 15.82 -> 18.46 | Improved |
| add novel view synthesis rendering to motion training (ablation) | MoVieS · DyCheck | mPSNR: 16.26 -> 18.46 | Improved |
| add novel view synthesis rendering to motion training (ablation) | MoVieS · Aria Digital Twin | EPE_3D: 0.3801 -> 0.2153 | Improved |
| initialize from VGGT instead of scratch (ablation) | MoVieS · DyCheck (224x224) | mPSNR: 16.64 -> 17.97 | Improved |
| train jointly on dynamic data with motion head vs static-only model | MoVieS · RealEstate10K | PSNR: 27.60 -> 26.98 | Hurt |
| MoVieS vs MoSca on NVIDIA scenes | MoVieS · NVIDIA dynamic scenes | PSNR: 21.45 -> 19.16 | Hurt |
Later papers that compared with this method
1 later accepted paper reports MoVieS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Taylor-Gaussians-Flow: Towards Non-uniform Motion for Novel View Synthesis from Monocular Video (ICML 2026 · better on 3 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- DepthSplat — DepthSplat: Connecting Gaussian Splatting and Depth (CVPR 2025) · better on 3 of 3 shared results
- MoSca — MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds (CVPR 2025) · better on 1 of 2 shared results
- SpatialTracker — SpatialTracker: Tracking Any 2D Pixels in 3D Space (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
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.91)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.91)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.90)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.89)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · similarity 0.89)
- OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos (ICML 2024 · similarity 0.89)
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.
