Research map / 3D vision / Depth and stereo
NLOST: Non-Line-of-Sight Imaging With Transformer
Read the paperCheck 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 |
|---|---|---|---|
| use NLOST instead of LFE | NLOS reconstruction · Seen testing data | PSNR: 26.90 -> 28.17 | Helped |
| use NLOST instead of LFE | NLOS reconstruction · Unseen testing data | PSNR: 23.40 -> 23.99 | Helped |
| add both spatial and temporal self-attention (ablation) | NLOST spatial-temporal self-attention encoder · Seen testing data | PSNR: 24.80 -> 26.41 | Helped |
| add temporal self-attention to spatial self-attention (ablation) | NLOST self-attention encoder · Seen testing data | PSNR: 24.80 -> 26.41 | Helped |
| add spatial self-attention to temporal self-attention (ablation) | NLOST self-attention encoder · Seen testing data | PSNR: 26.09 -> 26.41 | Helped |
| add both spatial and temporal cross-attention (ablation) | NLOST cross-attention decoder · Seen testing data | PSNR: 25.60 -> 26.41 | Helped |
| integrate local and global features on both branches (ablation) | NLOST cross-attention decoder · Seen testing data | PSNR: 25.82 -> 26.41 | Helped |
| add integration on the local branch to global-branch integration (ablation) | NLOST cross-attention decoder · Seen testing data | PSNR: 25.94 -> 26.41 | Helped |
| add integration on the global branch to local-branch integration (ablation) | NLOST cross-attention decoder · Seen testing data | PSNR: 26.06 -> 26.41 | Helped |
| add deep local features to deep global features (ablation) | NLOST feature fusion · Seen testing data | PSNR: 25.58 -> 26.33 | Helped |
| add shallow features to deep global and local features (ablation) | NLOST feature fusion · Seen testing data | PSNR: 26.33 -> 26.41 | Helped |
Closest papers by meaning
- Non-Line-of-Sight Imaging With Signal Superresolution Network (CVPR 2023 · similarity 0.90)
- Deep Non-line-of-sight Imaging from Under-scanning Measurements (NeurIPS 2023 · similarity 0.88)
- Deep Non-Line-of-Sight Reconstruction (CVPR 2020 · similarity 0.88)
- Dual-branch Graph Feature Learning for NLOS Imaging (AAAI 2025 · similarity 0.87)
- Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients (NeurIPS 2024 · similarity 0.86)
- NTO3D: Neural Target Object 3D Reconstruction with Segment Anything (CVPR 2024 · similarity 0.83)
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.