Research map / Detection and segmentation / Open-set and few-shot detection
Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery
Xiaosheng Yan, Feigege Wang, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jia Pan
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 coupled object and instance discriminators with 3D silhouette pool (ablation) | segmentation completion network · OVD synthetic | IoU: 0.7421 -> 0.7939 | Improved |
| add coupled object and instance discriminators with 3D silhouette pool (ablation) | segmentation completion network · OVD real | IoU: 0.8067 -> 0.8193 | Improved |
| add second inpainting path with shared generator during training (ablation) | appearance recovery network · OVD synthetic | SS: 0.8350 -> 0.9411 | Improved |
| add second inpainting path with shared generator during training (ablation) | appearance recovery network · OVD real | ICP: 0.8058 -> 0.8216 | Improved |
| run second iteration of refinement (ablation) | segmentation completion · OVD synthetic | IoU: 0.7939 -> 0.8137 | Improved |
| run second iteration of refinement (ablation) | segmentation completion · OVD real | IoU: 0.8066 -> 0.8067 | No clear effect |
| run third iteration instead of two (ablation) | segmentation completion · OVD synthetic | IoU: 0.8137 -> 0.8080 | Hurt |
| run third iteration instead of two (ablation) | segmentation completion · OVD real | IoU: 0.8067 -> 0.7926 | Hurt |
| run second iteration of refinement (ablation) | appearance recovery · OVD synthetic | SS: 0.9411 -> 0.9545 | Improved |
| run third iteration instead of two (ablation) | appearance recovery · OVD synthetic | SS: 0.9545 -> 0.8458 | Hurt |
| run second iteration of refinement with ground-truth masks given | appearance recovery · OVD synthetic, M^gt input | ICP: 0.7436 -> 0.7267 | Hurt |
| recover occluded vehicles before tracking | KCF tracker · Vid-3 | APE: 87.71 -> 21.51 | Improved |
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.
- SeGAN — SeGAN: Segmenting and Generating the Invisible (CVPR 2018) · better on 4 of 4 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
- Segment Anything, Even Occluded (CVPR 2025 · similarity 0.85)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (CVPR 2025 · similarity 0.84)
- Amodal Ground Truth and Completion in the Wild (CVPR 2024 · similarity 0.84)
- Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion (AAAI 2024 · similarity 0.84)
- O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model (AAAI 2024 · similarity 0.83)
- Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection (NeurIPS 2024 · similarity 0.83)
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.
