Research map / 3D vision / Depth and stereo
Gated2Depth: Real-Time Dense Lidar From Gated Images
Tobias Gruber, Frank Julca-Aguilar, Mario Bijelic, Felix Heide
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 |
|---|---|---|---|
| use three gated slices instead of the single full gated image (ablation) | Gated2Depth · Real night | RMSE (m): 14.86 -> 8.39 | Improved |
| use three gated slices instead of the single full gated image (ablation) | Gated2Depth · Real day | RMSE (m): 13.75 -> 7.61 | Improved |
| use learned Gated2DepthNet instead of per-pixel least squares | gated slices · Real night | RMSE (m): 13.13 -> 8.39 | Improved |
| use learned Gated2DepthNet instead of per-pixel least squares | gated slices · Real day | RMSE (m): 19.52 -> 7.61 | Improved |
| use learned Gated2DepthNet instead of per-pixel least squares | gated slices · Simulated night | RMSE (m): 30.45 -> 12.99 | Improved |
| use Gated2Depth instead of sparse-to-dense with GT lidar input | lidar-based depth completion · Real day | RMSE (m): 8.21 -> 7.61 | Improved |
| fine-tune monocular RGB model on real data | Depth from Mono on RGB · Real night | RMSE (m): 16.87 -> 11.41 | Improved |
| fine-tune monocular RGB model on real data | Depth from Mono on RGB · Real day | RMSE (m): 17.67 -> 10.24 | Improved |
| fine-tune monocular full-gated model on real data | Depth from Mono on Full Gated · Real night | RMSE (m): 16.26 -> 15.41 | Mixed |
| fine-tune monocular full-gated model on real data | Depth from Mono on Full Gated · Real day | RMSE (m): 13.89 -> 13.33 | Mixed |
| use gated slices rather than RGB-only or stereo input | depth estimation · Simulated night | RMSE (m): 72.67 -> 12.99 | Improved |
Closest papers by meaning
- Cross-spectral Gated-RGB Stereo Depth Estimation (CVPR 2024 · similarity 0.89)
- Gated Fields: Learning Scene Reconstruction from Gated Videos (CVPR 2024 · similarity 0.87)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.85)
- Flexible Depth Completion for Sparse and Varying Point Densities (CVPR 2024 · similarity 0.84)
- Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction (CVPR 2024 · similarity 0.84)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 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.
