Research map / 3D vision / Depth and stereo
DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image
Check 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 |
|---|---|---|---|
| add the surface normal pathway (ablation) | DeepLiDAR · KITTI depth completion validation set | RMSE (mm): 774.25 -> 687.00 | Helped |
| add attention-based integration of color and normal depth estimates (ablation) | DeepLiDAR · KITTI depth completion validation set | RMSE (mm): 729.96 -> 687.00 | Helped |
| use the Deep Completion Unit instead of early fusion (ablation) | DeepLiDAR · KITTI depth completion validation set | RMSE (mm): 767.82 -> 687.00 | Helped |
| use a learned confidence mask instead of a binary availability mask (ablation) | DeepLiDAR · KITTI depth completion validation set | RMSE (mm): 756.32 -> 687.00 | Helped |
| concatenate sparse-depth encoder features instead of summing them with decoder features (ablation) | DeepLiDAR DCU · KITTI depth completion validation set | RMSE (mm) | Hurt |
| combine sparse LiDAR depth and a color image using DeepLiDAR | DeepLiDAR · KITTI depth completion test set | RMSE (mm): 814.73 -> 758.38 | Helped |
| apply DeepLiDAR to indoor depth completion | DeepLiDAR · NYUv2 labeled test set | RMSE (m): 0.117 -> 0.115 | Helped |
Closest papers by meaning
- Flexible Depth Completion for Sparse and Varying Point Densities (CVPR 2024 · similarity 0.87)
- Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation (CVPR 2024 · similarity 0.86)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.86)
- Beyond Virtual Points: Depth-Enhanced LiDAR-only 3D Object Detection with Semi-Supervised Learning (Student Abstract) (AAAI 2025 · similarity 0.84)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.84)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · 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.