Research map / 3D vision / NeRF and radiance fields
DynPoint: Dynamic Neural Point For View Synthesis
Kaichen Zhou, Jia-Xing Zhong, Sangyun Shin, Kai Lu, Yiyuan Yang, Andrew Markham, Niki Trigoni
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 multiple-step (2K adjacent frame) aggregation (ablation) | DynPoint · Nvidia dynamic scenes | PSNR (avg): 14.78 -> 26.53 | Improved |
| use multiple-step (2K adjacent frame) aggregation (ablation) | DynPoint · Nvidia dynamic scenes | LPIPS (avg): 0.666 -> 0.068 | Improved |
| increase neighbouring frames from K=3 to K=6 (ablation) | DynPoint · Nvidia dynamic scenes | PSNR (avg): 18.94 -> 26.53 | Improved |
| increase neighbouring frames from K=3 to K=6 (ablation) | DynPoint · Nvidia dynamic scenes | LPIPS (avg): 0.357 -> 0.068 | Improved |
| add hierarchical neural point cloud (ablation) | DynPoint · Nvidia dynamic scenes | PSNR (avg): 24.38 -> 26.53 | Improved |
| add hierarchical neural point cloud (ablation) | DynPoint · Nvidia dynamic scenes | LPIPS (avg): 0.161 -> 0.068 | Improved |
| DynPoint versus RoDYN on LPIPS | DynPoint · Nvidia dynamic scenes | LPIPS (avg): 0.065 -> 0.068 | Hurt |
| DynPoint versus DynamicNeRF on PSNR | DynPoint · Nvidia dynamic scenes | PSNR (avg): 26.10 -> 26.53 | Improved |
| DynPoint versus NSFF | DynPoint · Nerfies dataset | PSNR (avg): 25.93 -> 26.41 | Improved |
| DynPoint versus NSFF | DynPoint · HyperNeRF dataset | PSNR (avg): 26.40 -> 27.50 | Improved |
| DynPoint versus Nerfies on LPIPS | DynPoint · Nerfies dataset | LPIPS (avg): 0.233 -> 0.241 | Hurt |
| DynPoint versus NSFF on iPhone | DynPoint · iPhone dataset | mPSNR (avg): 15.46 -> 16.89 | Improved |
Later papers that compared with this method
2 later accepted papers report DynPoint as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting (ECCV 2026 · better on 1 of 2 shared results)
- MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds (CVPR 2025 · better on 1 of 1 shared result)
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.
- D-NeRF — D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021) · 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
- DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting (ECCV 2024 · similarity 0.89)
- DyST: Towards Dynamic Neural Scene Representations on Real-World Videos (ICLR 2024 · similarity 0.87)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.87)
- DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 2024 · similarity 0.87)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.86)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · 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.
