Research map / 3D vision / Depth and stereo
DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs
Nikhil Behari, Diego Rivero, Luke Apostolides, Suman Ghosh, Paul Pu Liang, Ramesh Raskar
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 600 ps timing jitter blur (ablation) | NLOS localization · DENALI localization | RMSE: 0.0804 -> 0.0819 | Hurt |
| add 50 ps or 100 ps timing jitter blur (ablation) | NLOS localization · DENALI localization | RMSE: 0.0804 -> 0.0802 | No clear effect |
| add 600 ps timing jitter blur (ablation) | NLOS size classification · DENALI size classification | Accuracy: 0.8616 -> 0.7944 | Hurt |
| add 600 ps timing jitter blur (ablation) | NLOS object classification · DENALI object classification | Top-1: 0.1554 -> 0.1260 | Hurt |
| add 100 ps timing jitter blur (ablation) | NLOS object classification · DENALI object classification | Top-1: 0.1554 -> 0.1684 | Improved |
| use 1D CNN instead of MLP | histogram model · DENALI localization | RMSE: 0.1045 -> 0.0456 | Improved |
| use 1D CNN instead of Transformer | histogram model · DENALI localization | RMSE: 0.0579 -> 0.0456 | Improved |
| use 3D CNN (spatiotemporal) instead of 1D CNN | histogram model · DENALI localization | RMSE: 0.0456 -> 0.0475 | No clear effect |
| use 3D CNN instead of 1D CNN | histogram model · DENALI object classification | Top-1: 0.3876 -> 0.3523 | Hurt |
| use 3D CNN instead of 1D CNN | histogram model · DENALI object classification | Macro-F1: 0.3832 -> 0.4377 | Improved |
| use 8 inch objects instead of 4 inch | 1D CNN · DENALI localization | RMSE: 0.0548 -> 0.0341 | Improved |
| use 8 inch objects instead of 4 inch | 1D CNN · DENALI object classification | Top-1: 0.3191 -> 0.4573 | Improved |
Closest papers by meaning
- Robust 3D Object Detection using Probabilistic Point Clouds from Single-Photon LiDARs (ICCV 2025 · similarity 0.86)
- LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance (NeurIPS 2026 · similarity 0.85)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.85)
- Blurred LiDAR for Sharper 3D: Robust Handheld 3D Scanning with Diffuse LiDAR and RGB (CVPR 2025 · similarity 0.85)
- MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception (CVPR 2024 · similarity 0.85)
- Zero-Shot 4D Lidar Panoptic Segmentation (CVPR 2025 · similarity 0.85)
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.
