Research map / 3D vision / Human pose estimation
Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification
Feng Liu, Minchul Kim, ZiAng Gu, Anil Jain, Xiaoming Liu
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 the 3D shape modules instead of classification loss only (ablation) | 3DInvarReID · CCDA (trained on Celeb-reID) | Rank-1 (%): 28.4 -> 36.3 | Improved |
| add 3D clothing and texture modeling with rendering layer (ablation) | 3DInvarReID · CCDA (trained on Celeb-reID) | Rank-1 (%): 32.1 -> 36.3 | Improved |
| add 3D pre-training stage (ablation) | 3DInvarReID · CCDA (trained on Celeb-reID) | Rank-1 (%): 29.3 -> 36.3 | Improved |
| fuse 3D shape features with ReIDCaps by score summation | ReIDCaps · Celeb-reID-light | Rank-1 (%): 33.5 -> 42.2 | Improved |
| fuse 3D shape features with CAL on CCVID | CAL · CCVID cloth-changing | Rank-1 (%): 81.7 -> 84.3 | Improved |
| fuse 3D shape features with CAL on short-term ReID | CAL · Market-1501 and MSMT17 | Rank-1 (%): 94.7 -> 95.1 (Market-1501), 79.7 -> 80.8 (MSMT17) | Improved |
| use 3DInvarReID alone instead of CAL (single model, 2D features) | cloth-changing ReID · CCVID cloth-changing | Rank-1 (%): 81.7 -> 70.2 | Hurt |
| use 3DInvarReID alone instead of CAL on LTCC and PRCC | cloth-changing ReID · LTCC and PRCC | Rank-1 (%): 40.1 -> 37.8 (LTCC), 55.2 -> 51.6 (PRCC) | Hurt |
| train on Celeb-reID and test cross-domain with 3DInvarReID vs CAL | cloth-changing ReID · PRCC (cross-domain) | Rank-1 (%): 31.6 -> 40.7 | Improved |
| use 3DInvarReID naked-body shape fitting instead of SHAPY for reconstruction | 3D naked body reconstruction · HBW validation | Chamfer distance CD-L2: 0.632 -> 0.610 | Improved |
Closest papers by meaning
- Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification (CVPR 2021 · similarity 0.92)
- Learning Longterm Representations for Person Re-Identification Using Radio Signals (CVPR 2020 · similarity 0.90)
- Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation (CVPR 2024 · similarity 0.89)
- Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions (CVPR 2024 · similarity 0.89)
- DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID (CVPR 2025 · similarity 0.89)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.88)
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.
