Research map / 3D vision / NeRF and radiance fields
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 scene space annealing (ablation) | RegNeRF · DTU 3-view | Average: 0.291 -> 0.112 | Helped |
| add geometry regularization (ablation) | RegNeRF · DTU 3-view | Average: 0.188 -> 0.112 | Helped |
| add appearance regularization (ablation) | RegNeRF · DTU 3-view | Average: 0.117 -> 0.112 | Helped |
| use depth smoothness instead of opacity regularization (ablation) | RegNeRF · DTU 3-view | Average: 0.268 -> 0.112 | Helped |
| use depth smoothness instead of ray density entropy regularization (ablation) | RegNeRF · DTU 3-view | Average: 0.198 -> 0.112 | Helped |
| use depth smoothness instead of normal smoothness regularization (ablation) | RegNeRF · DTU 3-view | Average: 0.193 -> 0.112 | Helped |
| use depth smoothness instead of density surface regularization (ablation) | RegNeRF · DTU 3-view | Average: 0.184 -> 0.112 | Helped |
| use depth smoothness instead of sparsity regularization (ablation) | RegNeRF · DTU 3-view | Average: 0.145 -> 0.112 | Helped |
Closest papers by meaning
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.93)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.92)
- Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis? (CVPR 2024 · similarity 0.91)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.91)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.91)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.91)
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.