Research map / 3D vision / Face and shape
3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views
Xiaobiao Du, Yida Wang, Haiyang Sun, Zhuojie Wu, Hongwei Sheng, Shuyun Wang, Jiaying Ying, Ming Lu, Tianqing Zhu, Kun Zhan, Xin Yu
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 |
|---|---|---|---|
| increase simulated 3DRealCar training scenes from 1000 to 5000 (ablation) | YOLOv5n · CODA corner-case detection | mAP@0.5: 0.285 -> 0.361 | Improved |
| increase simulated 3DRealCar training scenes from 1000 to 5000 (ablation) | YOLOv5s · CODA corner-case detection | mAP@0.5: 0.341 -> 0.426 | Improved |
| increase simulated 3DRealCar training scenes from 1000 to 5000 (ablation) | YOLOv8n · CODA corner-case detection | mAP@0.5: 0.299 -> 0.386 | Improved |
| increase simulated 3DRealCar training scenes from 1000 to 5000 (ablation) | YOLOv8s · CODA corner-case detection | mAP@0.5: 0.371 -> 0.435 | Improved |
| increase simulated 3DRealCar training scenes from 1000 to 5000 (ablation) | CO-DETR · CODA corner-case detection | mAP@0.5: 0.465 -> 0.582 | Improved |
| increase simulated 3DRealCar training scenes from 1000 to 5000 (ablation) | YOLOv12x · CODA corner-case detection | mAP@0.5: 0.412 -> 0.565 | Improved |
| fine-tune Stable-Zero123 prior in Dreamcraft3D on 3DRealCar | Dreamcraft3D · single-image-to-3D | CLIP-I: 0.812 -> 0.847 | Improved |
| fine-tune Stable-Zero123 prior in Dreamcraft3D on 3DRealCar | Dreamcraft3D · single-image-to-3D | Hausdorff distance: 1.572 -> 1.364 | Improved |
| fine-tune Stable-Zero123 prior in Dreamcraft3D on 3DRealCar | Dreamcraft3D · single-image-to-3D | Chamfer Distance: 0.587 -> 0.371 | Improved |
| reflective lighting instead of standard lighting | 3DGS · 3DRealCar novel view synthesis | PSNR: 27.47 -> 24.58 | Hurt |
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.
- Dreamcraft3D — DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior (ICLR 2024) · better on 3 of 3 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
- ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving (CVPR 2019 · similarity 0.89)
- ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene Images (AAAI 2025 · similarity 0.89)
- Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images (CVPR 2026 · similarity 0.88)
- UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation (CVPR 2025 · similarity 0.87)
- SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset (NeurIPS 2024 · similarity 0.85)
- DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation (CVPR 2025 · similarity 0.84)
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.
