Research map / 3D vision / NeRF and radiance fields
Non-line-of-Sight Imaging via Neural Transient Fields
Siyuan Shen, Zi Wang, Ping Liu, Zhengqing Pan, Ruiqian Li, Tian Yi Gao, Shiying Li, Jingyi Yu A
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 the second training stage with loss-based resampling of spots (ablation) | NeTF · ZNLOS Bunny | reconstruction quality | Improved |
| add hierarchical (MCMC) sampling to two-stage training (ablation) | NeTF · ZNLOS Bunny | reconstruction quality | Improved |
| use NeTF instead of DLCT | DLCT · ZNLOS Lucy (confocal) | MAE (cm): 0.23 cm -> 1.05 cm | Hurt |
| use NeTF instead of Phasor Field | Phasor Field · ZNLOS Lucy (confocal) | MAE (cm): 1.36 cm -> 1.05 cm | Improved |
| use NeTF instead of Phasor Field | Phasor Field · ZNLOS Indonesian (confocal) | MAE (cm): 1.69 cm -> 0.31 cm | Improved |
| use NeTF instead of FBP | FBP · ZNLOS Z (non-confocal) | MAE (cm): 0.46 cm -> 0.60 cm | Hurt |
| use NeTF instead of BP | BP · ZNLOS Bunny (non-confocal) | MAE (cm): 7.02 cm -> 7.45 cm | Hurt |
| downsample wall spots from 256x256 to 16x16 or 8x8 | NeTF · ZNLOS Bunny | reconstruction quality | No clear effect |
Closest papers by meaning
- NLOS-NeuS: Non-line-of-sight Neural Implicit Surface (ICCV 2023 · similarity 0.90)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.87)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.86)
- NeISF: Neural Incident Stokes Field for Geometry and Material Estimation (CVPR 2024 · similarity 0.86)
- Learning Neural Exposure Fields for View Synthesis (NeurIPS 2025 · similarity 0.86)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.86)
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.
