Research map / Detection and segmentation / 3D detection and driving
LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-Based 3D Detector
Xiaoyang Guo, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li
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 LiDAR feature imitation (ablation) | stereo baseline (b) · KITTI val Car AP3D Mod | AP3D: 62.74 -> 65.67 | Improved |
| add LiDAR feature imitation (ablation) | stereo baseline (b) · KITTI val Pedestrian AP3D Mod | AP3D: 33.72 -> 38.89 | Improved |
| add LiDAR feature imitation (ablation) | stereo baseline (b) · KITTI val Cyclist AP3D Mod | AP3D: 26.77 -> 33.70 | Improved |
| add auxiliary 2D detection head (ablation) | stereo baseline (b) · KITTI val Car AP3D Mod | AP3D: 62.74 -> 63.32 | Improved |
| add auxiliary 2D detection head (ablation) | stereo baseline (b) · KITTI val Cyclist AP3D Mod | AP3D: 26.77 -> 30.26 | Improved |
| add auxiliary 2D detection head (ablation) | stereo baseline (b) · KITTI val Pedestrian AP3D Mod | AP3D: 33.72 -> 34.23 | Improved |
| add 2D head on top of imitation (ablation) | model (c) · KITTI val Car AP3D Mod | AP3D: 65.67 -> 65.64 | No clear effect |
| add trick set (full-res features, IoU loss, uni-modal depth loss) (ablation) | DSGN re-implementation (a) · KITTI val Car AP3D Mod | AP3D: 56.73 -> 62.74 | Improved |
| add ImageNet pretrained weights for conv1-3 (ablation) | baseline (b) · KITTI val Car AP3D Mod | AP3D: 62.74 -> 63.07 | Improved |
| add foreground mask M_fg to imitation loss (ablation) | LIGA-Stereo imitation · KITTI val Car AP3D Mod | AP3D: 62.01 -> 65.67 | Improved |
| imitate all three feature layers instead of V3d and aggregated BEV (ablation) | LIGA-Stereo imitation · KITTI val Car AP3D Mod | AP3D: 65.67 -> 63.49 | Hurt |
| vary imitation weight lambda_im from 1.0 to 0.2 (ablation) | LIGA-Stereo imitation · KITTI val Car AP3D Mod | AP3D: 65.67 -> 64.15 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DSGN — DSGN: Deep Stereo Geometry Network for 3D Object Detection (CVPR 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Advancing 3D Object Detection With Depth-Aware Spatial Knowledge Distillation (TPAMI 2025 · similarity 0.90)
- Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving (CVPR 2022 · similarity 0.90)
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (CVPR 2018 · similarity 0.90)
- MonoDistill: Learning Spatial Features for Monocular 3D Object Detection (ICLR 2022 · similarity 0.90)
- Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving (CVPR 2019 · similarity 0.90)
- DSGN: Deep Stereo Geometry Network for 3D Object Detection (CVPR 2020 · similarity 0.90)
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.
