Research map / 3D vision / Gaussian splatting
DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting
Angelos Kratimenos, Jiahui Lei, Kostas Daniilidis
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 a learned MLP time-basis instead of a Fourier basis (ablation) | DynMF · D-NeRF Mutant | PSNR (dB): 33.17 -> 40.79 | Improved |
| use a learned basis instead of Fourier 10 (ablation) | DynMF · N3DV Flame-steak | PSNR (dB): 28.95 -> 31.57 | Improved |
| increase number of trajectories from 1 to 10 (ablation) | DynMF · D-NeRF Mutant | PSNR (dB): 29.75 -> 40.79 | Improved |
| increase number of trajectories beyond 10 (20 or 50) (ablation) | DynMF · D-NeRF Mutant | PSNR (dB): 40.79 -> 40.53 | No clear effect |
| increase time positional-encoding frequencies from 1 to 32 (ablation) | DynMF · N3DV Flame-steak | PSNR (dB): 29.32 -> 31.57 | Improved |
| increase time encoding from 32 to 60 frequencies (ablation) | DynMF · N3DV Flame-steak | PSNR (dB): 31.57 -> 29.80 | Hurt |
| add a rigidity loss on motion coefficients (ablation) | DynMF · dynamic scenes | render quality | No clear effect |
| use DynMF instead of 4DGS and Gaufre | dynamic 3D Gaussian splatting · D-NeRF | PSNR (dB): 34.80 -> 36.89 | Improved |
| use DynMF instead of 4DGS | dynamic 3D Gaussian splatting · N3DV | PSNR (dB): 32.01 -> 31.70 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- Hexplane — HexPlane: A Fast Representation for Dynamic Scenes (CVPR 2023) · better on 0 of 1 shared result
- D-NeRF — D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021) · better on 1 of 1 shared result
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 0.90)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.90)
- Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis (CVPR 2024 · similarity 0.89)
- Dynamic 3D Gaussian Fields for Urban Areas (NeurIPS 2024 · similarity 0.89)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.89)
- SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 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.
