Research map / Detection and segmentation / 3D detection and driving
RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving
Peixuan Li, Shun Su, Huaici Zhao
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 |
|---|---|---|---|
| use FCE space instead of PSMNet-derived occupancy space (ablation) | RTS3D · KITTI val car, IoU>0.7, Moderate | AP3D: 23.53 -> 43.54 | Improved |
| add StrAA to FCE Space (ablation) | RTS3D · KITTI val car, IoU>0.7, Moderate | AP3D: 43.54 -> 45.18 | Improved |
| use channel-keeping RBF rather than absolute difference (ablation) | RTS3D · KITTI val car, IoU>0.7, Moderate | AP3D: 39.54 -> 45.18 | Improved |
| replace RBF with concatenation and MLP (ablation) | RTS3D · KITTI val car, IoU>0.7, Moderate | AP3D: 45.18 -> 13.03 | Hurt |
| reduce channels in the consistency representation (ablation) | RTS3D · KITTI val car, IoU>0.7, Moderate | AP3D: 45.18 -> 23.53 | Hurt |
| switch initial latent-space detector between CenterNet and KMNet (ablation) | RTS3D · KITTI val car, IoU>0.5, Moderate | AP3D: 78.18 vs 78.27 | No clear effect |
| increase iterations beyond 1 (ablation) | RTS3D · KITTI val | detection accuracy | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- ZoomNet — Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition (ECCV 2018) · better on 0 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
- IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving (CVPR 2020 · similarity 0.89)
- LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-Based 3D Detector (ICCV 2021 · similarity 0.89)
- Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving (CVPR 2022 · similarity 0.89)
- Stereo R-CNN Based 3D Object Detection for Autonomous Driving (CVPR 2019 · similarity 0.88)
- SOGDet: Semantic-Occupancy Guided Multi-View 3D Object Detection (AAAI 2024 · similarity 0.87)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (CVPR 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.
