Research map / Point clouds / Point cloud classification
DVI: Depth Guided Video Inpainting for Autonomous Driving
Miao Liao, Feixiang Lu, Dingfu Zhou, Sibo Zhang, Wei Li, Ruigang Yang
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 Poisson color blending (ablation) | DVI · Own dataset, Poisson blending ablation | RMSE: 17.484 -> 13.009 | Improved |
| add Poisson color blending (ablation) | DVI · Own dataset, Poisson blending ablation | MAE: 9.410 -> 6.497 | Improved |
| add Poisson color blending (ablation) | DVI · Own dataset, Poisson blending ablation | PSNR: 21.783 -> 22.312 | Improved |
| add Poisson color blending (ablation) | DVI · Own dataset, Poisson blending ablation | SSIM: 0.911 -> 0.917 | Improved |
| add multi-video fusion (ablation) | DVI · Own dataset, video fusion ablation | RMSE: 14.967 -> 8.333 | Improved |
| add multi-video fusion (ablation) | DVI · Own dataset, video fusion ablation | MAE: 10.427 -> 6.059 | Improved |
| add multi-video fusion (ablation) | DVI · Own dataset, video fusion ablation | PSNR: 20.941 -> 21.195 | Improved |
| add multi-video fusion (ablation) | DVI · Own dataset, video fusion ablation | SSIM: 0.879 -> 0.882 | Improved |
| use depth-guided inpainting instead of Huang et al. | video inpainting · Own driving inpainting dataset (quantitative comparison) | RMSE: 11.017 -> 9.633 | Improved |
| use depth-guided inpainting instead of Xu et al. | video inpainting · Own driving inpainting dataset (quantitative comparison) | SSIM: 0.594 -> 0.895 | Improved |
| use depth-guided inpainting instead of Yu et al. (GAN image inpainting) | image inpainting · Own driving inpainting dataset (quantitative comparison) | PSNR: 20.821 -> 21.631 | Improved |
Closest papers by meaning
- DriveWeaver: Point-Conditioned Video Inpainting for Controllable Vehicle Insertion in Autonomous Driving Simulation (ECCV 2026 · similarity 0.87)
- 3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline (ICLR 2025 · similarity 0.85)
- Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis (NeurIPS 2026 · similarity 0.85)
- LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes (CVPR 2024 · similarity 0.84)
- SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction (CVPR 2025 · similarity 0.84)
- STViT: Improving Self-Supervised Multi-Camera Depth Estimation with Spatial-Temporal Context and Adversarial Geometry Regularization (Student Abstract) (AAAI 2024 · 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.
