Research map / 3D vision / NeRF and radiance fields
D^2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video
Tianhao Walter Wu, Fangcheng Zhong, Andrea Tagliasacchi, Forrester Cole, Cengiz Oztireli
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 D2NeRF's added static component instead of HyperNeRF baseline alone | D2NeRF · Novel view synthesis mean | PSNR: 18.91 -> 21.39 | Improved |
| Compare to HyperNeRF widened to match parameter count (HN fair) | D2NeRF · Novel view synthesis mean | PSNR: 18.82 -> 21.39 | Improved |
| Widen HyperNeRF MLP to 375 to match parameters (fair version) | HyperNeRF · Novel view synthesis mean | LPIPS: .304 -> .291 | No clear effect |
| Use D2NeRF vs NeuralDiff | D2NeRF · Novel view synthesis mean | MS-SSIM: .784 -> .836 | Improved |
| Use D2NeRF vs NeuralDiff | D2NeRF · Pick2 scene | PSNR: 21.81 -> 20.32 | Hurt |
| Use D2NeRF vs NeuralDiff | D2NeRF · Water scene | PSNR: 18.36 -> 21.63 | Improved |
| Use D2NeRF vs HyperNeRF fair | D2NeRF · Banana scene | PSNR: 21.52 -> 21.35 | No clear effect |
| Use D2NeRF vs HyperNeRF base | D2NeRF · Pick2 scene | PSNR: 13.06 -> 20.32 | Improved |
| Add skewed binary entropy regularization (skew k>1) (ablation) | D2NeRF · Synthetic scene decoupling | decoupling quality | Improved |
| Over-skew the binary entropy (large k) (ablation) | D2NeRF · Static background rendering | floaters | Hurt |
| Add density ratio ray regularization L_r (ablation) | D2NeRF · Synthetic scene decoupling | decoupling quality | Improved |
| Add shadow field network (ablation) | D2NeRF · Real scenes with large, slow or repetitive shadows | shadow decoupling | Improved |
Closest papers by meaning
- DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 2024 · similarity 0.87)
- EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision (ICLR 2024 · similarity 0.86)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.86)
- Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos (CVPR 2025 · similarity 0.85)
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · similarity 0.85)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.85)
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.
