Research map / 3D vision / NeRF and radiance fields
Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modeling
Jaehyeok Kim, Dongyoon Wee, Dan Xu
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 pose-embedded implicit features to the non-rigid branch (ablation) | MoCo-NeRF · ZJU-MoCap (single-subject) | PSNR: 30.64 -> 31.06 | Improved |
| add radiance residual (non-rigid) branch on top of the rigid branch (ablation) | MoCo-NeRF · ZJU-MoCap (single-subject) | LPIPS x1000: 29.93 -> 28.83 | Improved |
| use cross-attention to generate the pose-embedded feature (ablation) | MoCo-NeRF · ZJU-MoCap (single-subject) | LPIPS x1000: 30.66 -> 28.83 | Improved |
| share frozen canonical features with the residual branch instead of unfrozen or no sharing (ablation) | MoCo-NeRF · ZJU-MoCap (single-subject) | LPIPS x1000: 30.17 (no sharing), 30.71 (unfrozen) -> 28.83 | Improved |
| add identity codes for multi-subject training (ablation) | multi-subject MoCo-NeRF · ZJU-MoCap (multi-subject) | PSNR: 28.63 -> 30.70 | Improved |
| add N_s local MHEs for multi-subject training (ablation) | multi-subject MoCo-NeRF · ZJU-MoCap (multi-subject) | PSNR: 28.63 -> 30.86 | Improved |
| add global MHE shared across subjects (ablation) | multi-subject MoCo-NeRF · ZJU-MoCap (multi-subject) | LPIPS x1000: 28.49 -> 27.69 | Improved |
| split one MHE's features between rigid and non-rigid branches instead of two separate MHEs (ablation) | MoCo-NeRF · training and rendering speed | speed overhead: avoids x1.14 slowdown | Improved |
| replace HumanNeRF canonical and non-rigid MLPs with MHEs (ablation) | HumanNeRF · ZJU-MoCap | qualitative rendering | Hurt |
| train longer | GauHuman and Instant-NVR · ZJU-MoCap | non-rigid motion quality | Hurt |
| MoCo-NeRF vs HumanNeRF on MonoCap perceptual metric | MoCo-NeRF · MonoCap (single-subject) | LPIPS x1000: 12.93 (HumanNeRF) vs 13.02 | No clear effect |
| use MoCo-NeRF instead of HumanNeRF for training efficiency (6 subjects) | MoCo-NeRF · ZJU-MoCap (6 subjects) | train time (hours): 233.3 -> 2.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- HumanNeRF — HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (CVPR 2022) · better on 4 of 5 shared results
- GauHuman — GauHuman: Articulated Gaussian Splatting from Monocular Human Videos (CVPR 2024) · better on 1 of 1 shared result
- Instant-NVR — Instant-NVR: Instant Neural Volumetric Rendering for Human-Object Interactions From Monocular RGBD Stream (CVPR 2023) · 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
- H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion (NeurIPS 2021 · similarity 0.91)
- A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose (NeurIPS 2021 · similarity 0.90)
- Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video (ICCV 2021 · similarity 0.90)
- Learning Compositional Radiance Fields of Dynamic Human Heads (CVPR 2021 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.88)
- SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering (CVPR 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.
