Research map / Detection and segmentation / 3D detection and driving
Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving
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 |
|---|---|---|---|
| Use feature-level Pseudo-Stereo generation with disparity-wise dynamic convolution and depth loss instead of feature-clone with depth loss (ablation) | LIGA-Stereo-based monocular detector · KITTI val, Car, Moderate | AP3D: 19.15 -> 24.15 | Helped |
| Add depth loss to feature-level generation (ablation) | Feature-level Pseudo-Stereo · KITTI val, Car, Moderate | AP3D: 16.18 -> 24.15 | Helped |
| Add depth loss to image-level generation (ablation) | Image-level Pseudo-Stereo · KITTI val, Car, Moderate | AP3D: 22.36 -> 21.53 | Hurt |
| Add depth loss to feature-clone (ablation) | Feature-clone Pseudo-Stereo · KITTI val, Car, Moderate | AP3D: 17.09 -> 19.15 | Helped |
| Use estimated depth information to generate a virtual view at image level (ablation) | Image-level Pseudo-Stereo · KITTI val, Car, Moderate | AP3D: 17.09 -> 22.36 | Helped |
| Use estimated depth information in feature-level generation (ablation) | Feature-level Pseudo-Stereo · KITTI val, Car, Moderate | AP3D: 17.09 -> 16.18 | Helped |
| Replace image-level warping with adaptive feature-level generation and depth loss (ablation) | LIGA-Stereo-based monocular detector · KITTI val, Car, Moderate | AP3D: 22.36 -> 24.15 | Helped |
| Use feature-level Pseudo-Stereo detection rather than DD3D | KITTI monocular 3D detection · KITTI test, Car, Moderate | AP3D: 16.34 -> 17.74 | Helped |
| Use feature-level Pseudo-Stereo detection rather than GUPNet | KITTI monocular 3D detection · KITTI test, Pedestrian, Moderate | AP3D: 9.76 -> 10.82 | Helped |
| Use feature-level Pseudo-Stereo detection rather than MonoPSR | KITTI monocular 3D detection · KITTI test, Cyclist, Moderate | AP3D: 4.74 -> 6.18 | Helped |
Closest papers by meaning
- Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving (CVPR 2019 · similarity 0.93)
- Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving (ICLR 2020 · similarity 0.93)
- End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection (CVPR 2020 · similarity 0.90)
- IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving (CVPR 2020 · similarity 0.90)
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · similarity 0.88)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.88)
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.