Research map / Detection and segmentation / Open-set and few-shot detection
WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery
N. Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan
Check 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 |
|---|---|---|---|
| Train on Clip Art WALT (CWALT) rather than human-annotated data | Amodal segmentation methods · SWALT | amodal segmentation: 79.4 -> 83.1; 82.79 -> 89.9; 83.6 -> 92.19 | Improved |
| Add occluder and occluded-layer features to the amodal object network (ablation) | WALT-Net · RWALT and CWALT | segmentation accuracy: RWALT: 55.3 -> 68.1; CWALT: 62.3 -> 75.3 | Improved |
| Combine boundary and segmentation-mask supervision (ablation) | WALT-Net · RWALT and CWALT | segmentation accuracy: RWALT AO: 55.3 -> 60.5 -> 61.4; CWALT AO: 62.3 -> 65.5 -> 66.1 | Improved |
| Use longitudinally mined unoccluded objects to train amodal representations | WALT-Net · SWALT | amodal segmentation: 78.2 -> 92.19 | Improved |
Closest papers by meaning
- WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects Under Occlusion (CVPR 2024 · similarity 0.90)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (CVPR 2025 · similarity 0.88)
- 3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline (ICLR 2025 · similarity 0.87)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (NeurIPS 2025 · similarity 0.86)
- Using Diffusion Priors for Video Amodal Segmentation (CVPR 2025 · similarity 0.85)
- Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis (NeurIPS 2026 · 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.
