Research map / 3D vision / NeRF and radiance fields
Learning Neural Scene Representation from iToF Imaging
Wenjie Chang, Hanzhi Chang, Yueyi Zhang, Wenfei Yang, Tianzhu 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 |
|---|---|---|---|
| add phase supervision (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | MAE: 0.3712 -> 0.0468 | Improved |
| add amplitude supervision (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | MAE: 2.9484 -> 0.0468 | Improved |
| add wrapping-aware phase-to-depth loss Lw (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | MAE: 0.9039 -> 0.0535 | Improved |
| add phase-guided sampling on top of Lw (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | MAE: 0.0535 -> 0.0510 | Improved |
| add phase-guided sampling without Lw (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | MAE: 0.9039 -> 0.3901 | Improved |
| add noise-weight loss Ln (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | MAE: 0.0510 -> 0.0468 | Improved |
| add noise-weight loss Ln (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | delta1: 0.9881 -> 0.9946 | Improved |
| raise modulation frequency from 20 MHz to 60 MHz (ablation) | iToF neural SDF · Synthetic iToF (6-scene average, 60 MHz) | MAE: 0.1018 -> 0.0468 | Improved |
| multi-view neural fusion versus raw MPI-affected depth (20 MHz) | iToF neural SDF · Synthetic iToF Veach-ajar (20 MHz) | MAE: 0.2251 -> 0.1148 | Improved |
| use SDF amplitude rendering instead of NeuS rendering (NeuS-ToF) (ablation) | iToF neural SDF · Synthetic iToF Bathroom2 (60 MHz) | MAE: 2.3439 -> 0.0427 | Improved |
Closest papers by meaning
- iToF-flow-based High Frame Rate Depth Imaging (CVPR 2024 · similarity 0.87)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.86)
- Denoising Diffusion via Image-Based Rendering (ICLR 2024 · similarity 0.85)
- Learning Neural Exposure Fields for View Synthesis (NeurIPS 2025 · similarity 0.85)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.85)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.84)
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.
