Research map / Detection and segmentation / 3D detection and driving
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection
Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Huimin Ma, Sanja Fidler, Raquel Urtasun
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 orientation regression loss (ablation) | detection network · KITTI val Cars Moderate | AOS: 38.24 -> 85.80 | Improved |
| add orientation regression loss (ablation) | detection network · KITTI val Cars Moderate | AP_2D: 87.26 -> 87.52 | No clear effect |
| add contextual branch (ablation) | detection network · KITTI val Cars Moderate | AP_2D: 87.52 -> 88.07 | Improved |
| add contextual branch (ablation) | detection network · KITTI val Pedestrians Moderate | AP_2D: 69.42 -> 64.46 | Hurt |
| add class-specific weights in proposal generation (ablation) | detection network · KITTI val Cars Moderate | AP_2D: 87.30 -> 88.07 | Improved |
| use class-specific proposals instead of class-independent variant (ablation) | proposal generation · KITTI 2D box recall | recall | Improved |
| replace Selective Search proposals with ours (ablation) | detection network · KITTI val Cars Moderate | AP_2D: 60.00 -> 88.07 | Improved |
| replace EdgeBoxes proposals with ours (ablation) | detection network · KITTI val Cars Moderate | AP_2D: 70.47 -> 88.07 | Improved |
| add HHA depth stream (two-stream RGB-HHA) (ablation) | detection network, hybrid data · KITTI val Cars Moderate | AP_3D: 75.86 -> 81.21 | Improved |
| add HHA depth stream (two-stream RGB-HHA) (ablation) | detection network, stereo data · KITTI val Cars Moderate | AP_3D: 56.97 -> 68.90 | Improved |
| add HHA depth stream (ablation) | detection network · KITTI val Cars | AP_2D | No clear effect |
| use LIDAR instead of stereo proposals (ablation) | proposal generation · KITTI val Cars Moderate | AP_3D: 69.52 -> 73.56 | Improved |
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.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 8 of 8 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
- Stereo R-CNN Based 3D Object Detection for Autonomous Driving (CVPR 2019 · similarity 0.93)
- Monocular 3D Object Detection for Autonomous Driving (CVPR 2016 · similarity 0.92)
- M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (ICCV 2019 · similarity 0.91)
- IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving (CVPR 2020 · similarity 0.91)
- Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving (CVPR 2019 · similarity 0.91)
- LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving (CVPR 2019 · 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.
