Research map / 3D vision / Depth and stereo
Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera
Hongrui Cai, Wanquan Feng, Xuetao Feng, Yan Wang, Juyong 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 |
|---|---|---|---|
| use NDR instead of RGB-D fusion baselines | Dynamic scene reconstruction · DeepDeform Dog | mean geometry error: 92.53 -> 3.42 | Improved |
| use NDR instead of OcclusionFusion | Dynamic scene reconstruction · KillingFusion Hat | mean geometry error: 6.77 -> 4.93 | Improved |
| use NDR instead of OcclusionFusion | Dynamic scene reconstruction · KillingFusion Alex | mean geometry error: 3.75 -> 4.24 | Hurt |
| add depth-image supervision to RGB-only NDR (ablation) | NDR · DeepDeform and KillingFusion qualitative sequences | reconstruction geometry quality | Improved |
| add RGB-image and color-loss supervision to depth-only NDR (ablation) | NDR · dynamic reconstruction qualitative sequences | geometric detail | Improved |
| replace the bijective map with 6D motion (ablation) | NDR · Rotated Body | cycle consistency error: 5.29 -> 473.25 | Hurt |
| replace the bijective map with 6D motion (ablation) | NDR · Talking Head | cycle consistency error: 4.97 -> 289.41 | Hurt |
| remove the topology-aware network F_q (ablation) | NDR · topology-varying regions, including human face eyes and mouth | topology-varying geometry and motion quality | Hurt |
| remove the visible loss term (ablation) | NDR with depth supervision · depth-only qualitative reconstruction | local geometry quality | Hurt |
| increase camera-pose initialization noise | NDR · Moving Joints | mean geometry error (mm): 2.95 -> 30.28 | Hurt |
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.
- OcclusionFusion — OcclusionFusion: Occlusion-Aware Motion Estimation for Real-Time Dynamic 3D Reconstruction (CVPR 2022) · better on 10 of 12 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
- MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video (CVPR 2024 · similarity 0.91)
- NeuralRecon: Real-Time Coherent 3D Reconstruction From Monocular Video (CVPR 2021 · similarity 0.88)
- NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos (NeurIPS 2022 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.88)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.87)
- TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene (NeurIPS 2024 · similarity 0.87)
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.
