Research map / 3D vision / NeRF and radiance fields
Dynamic Mesh-Aware Radiance Fields
Yi-Ling Qiao, Alexander Gao, Yiran Xu, Yue Feng, Jia-Bin Huang, Ming C. Lin
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 hybrid mesh-NeRF light transport instead of 2D compositing or mesh extraction for virtual object insertion | Mesh insertion into NeRF scenes · User study (Mirror, Garden, Bicycle) | participants ranking method first: 13/15, 12/15 and 15/15 ranked ours highest; p = 0.035, 0.007 | Improved |
| Train NeRF on 32-bit HDR images instead of 8-bit LDR (ablation) | Hybrid renderer · Qualitative lighting on inserted mesh | lighting realism (qualitative) | Improved |
| Use learned SDF (NeuS-NGP) as collision geometry instead of marching-cubes mesh from density field (ablation) | Simulation · Four balls on countertop | collision correctness (qualitative): 2 of 4 balls sink with density mesh | Improved |
| Use SDF-based hybrid simulation instead of NeuPhysics hexahedra mesh simulation | Bouncing ball simulation · Run time comparison | run time: 25x-50x faster | Improved |
| Increase number of inserted objects from 1 to 10^4 (ablation) | Simulation and rendering modules · Fox scene profiling | memory and run time: memory 0.5 GB and 1.0 GB constant; run time linear | Mixed |
| Use standard LDR NeRF instead of HDR NeRF (ablation) | Hybrid renderer · Qualitative | visual results | No clear effect |
Closest papers by meaning
- A General Implicit Framework for Fast NeRF Composition and Rendering (AAAI 2024 · similarity 0.91)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.90)
- Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption (AAAI 2024 · similarity 0.90)
- Physical-aware Neural Radiance Fields for Efficient Exposure Correction (AAAI 2025 · similarity 0.89)
- Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields (AAAI 2024 · similarity 0.89)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.89)
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.
