Research map / 3D vision / 3D generation
ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for 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 |
|---|---|---|---|
| add mask pooling (ablation) | 3D-RCNN* · ApolloCar3D test | A3DP-Abs mean: 16.44 -> 16.73 | Helped |
| add mask pooling (ablation) | 3D-RCNN* · ApolloCar3D test | A3DP-Rel mean: 10.79 -> 10.10 | Hurt |
| add offset flow alongside mask pooling (ablation) | 3D-RCNN* · ApolloCar3D test | A3DP-Abs mean: 16.44 -> 17.52 | Helped |
| add offset flow alongside mask pooling (ablation) | 3D-RCNN* · ApolloCar3D test | A3DP-Rel mean: 10.79 -> 13.66 | Helped |
| use predicted Mask R-CNN masks instead of ground-truth masks (ablation) | 3D-RCNN* + MP + OF · ApolloCar3D test | A3DP-Abs mean: 17.52 -> 15.15 | Hurt |
| use predicted Mask R-CNN masks instead of ground-truth masks (ablation) | 3D-RCNN* + MP + OF · ApolloCar3D test | A3DP-Rel mean: 13.66 -> 11.49 | Hurt |
| add context-aware solver to use neighboring-car constraints for insufficient keypoints (ablation) | DeepMANTA* · ApolloCar3D test | A3DP-Abs mean: 20.10 -> 21.57 | Helped |
| add context-aware solver to use neighboring-car constraints for insufficient keypoints (ablation) | DeepMANTA* · ApolloCar3D test | A3DP-Rel mean: 16.04 -> 17.52 | Helped |
| use predicted Mask R-CNN masks instead of ground-truth masks (ablation) | DeepMANTA* + CA-solver · ApolloCar3D test | A3DP-Abs mean: 21.57 -> 20.39 | Hurt |
| use predicted Mask R-CNN masks instead of ground-truth masks (ablation) | DeepMANTA* + CA-solver · ApolloCar3D test | A3DP-Rel mean: 17.52 -> 16.53 | Hurt |
Closest papers by meaning
- ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene Images (AAAI 2025 · similarity 0.88)
- Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement (AAAI 2025 · similarity 0.86)
- UniPAD: A Universal Pre-training Paradigm for Autonomous Driving (CVPR 2024 · similarity 0.86)
- DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation (CVPR 2025 · similarity 0.86)
- OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection (NeurIPS 2025 · similarity 0.86)
- 3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving (AAAI 2025 · similarity 0.85)
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.