Research map / 3D vision / Depth and stereo
"JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes"
Haimei Zhao, Jing Zhang, Sen Zhang, Dacheng Tao
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 cross-view transfer (CCT-CV) (ablation) | baseline 1-1 · Argoverse road layout | mIoU: 76.66 -> 77.76 | Improved |
| add cross-modal transfer (CCT-CM) on top of CCT-CV (ablation) | baseline 1-1 · Argoverse road layout | mAP: 88.42 -> 89.00 | Improved |
| add complete CCT (ablation) | baseline 1-1 · Argoverse vehicle layout | mIoU: 46.97 -> 49.39 | Improved |
| add hybrid loss (ablation) | 1-1 with CCT · Argoverse road layout | mAP: 89.00 -> 90.59 | Improved |
| share one encoder for road and vehicle layouts (ablation) | baseline · Argoverse vehicle layout | mIoU: 46.97 -> 42.77 | Hurt |
| add CCT and hybrid loss to shared-encoder baseline (ablation) | baseline 1-2 · Argoverse vehicle layout | mIoU: 42.77 -> 49.45 | Improved |
| use shared encoder for depth and layout networks (ablation) | JPerceiver · KITTI Odometry road layout | mIoU: 78.13 -> 77.53 | Hurt |
| use shared encoder for depth and layout networks (ablation) | JPerceiver · KITTI Odometry VO sequence 07 | t_err (%): 4.57 -> 9.73 | Hurt |
| use shared encoder for depth and layout networks (ablation) | JPerceiver · KITTI Odometry depth (1024x1024) | Abs Rel: 0.116 -> 0.133 | Hurt |
| add CCT (ablation) | depth baseline · KITTI Odometry depth (512x512) | Abs Rel: 0.120 -> 0.108 | Improved |
| add CGT scale loss (ablation) | depth baseline · KITTI Odometry depth (512x512) | Abs Rel: 0.120 -> 0.135 | Hurt |
| add CGT scale loss (ablation) | depth baseline · KITTI Odometry depth (512x512) | scale factor: 39.452 -> 1.088 | Improved |
Closest papers by meaning
- Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation (ECCV 2026 · similarity 0.89)
- Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation (CVPR 2021 · similarity 0.88)
- LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving (CVPR 2026 · similarity 0.87)
- Monocular BEV Perception of Road Scenes via Front-to-Top View Projection (TPAMI 2024 · similarity 0.87)
- VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- UniDrive: Towards Universal Driving Perception Across Camera Configurations (ICLR 2025 · similarity 0.86)
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.
