Research map / 3D vision / Face and shape
Shape-Pose Ambiguity in Learning 3D Reconstruction from Images
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the proposed pose-independent GAN, pseudo pose regressor, and view-discrimination reconstruction without pose labels instead of VPL's pose-supervised method | Single-view 3D reconstruction · ShapeNet test (Mean) | IoU: .505 -> .489 | Hurt |
| Use the proposed method without pose labels instead of VPL's pose-supervised method | Single-view 3D reconstruction · ShapeNet test (Mean) | CD (x0.01): 2.74 -> 3.38 | Hurt |
| Use the proposed method instead of the pose-unsupervised re-projection baseline | Single-view 3D reconstruction · ShapeNet test (Mean) | IoU: .277 -> .489 | Helped |
| Use the proposed method instead of the pose-unsupervised re-projection baseline | Single-view 3D reconstruction · ShapeNet test (Mean) | CD (x0.01): 7.97 -> 3.38 | Helped |
| Add learned reconstruction trained with re-projection loss rather than using the generated shape manifold directly (ablation) | Shape manifold reconstruction · ShapeNet airplane, car, and chair | IoU: airplane .476 -> .521; car .556 -> .652; chair .361 -> .439 | Helped |
| Replace the pose-independent discriminator with a pose-aware discriminator (ablation) | 3D reconstruction network · ShapeNet airplane, car, and chair | IoU: airplane .521 -> .410; car .652 -> .344; chair .439 -> .325 | Hurt |
Closest papers by meaning
- Unsupervised Learning of Shape and Pose with Differentiable Point Clouds (NeurIPS 2018 · similarity 0.90)
- Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction (CVPR 2018 · similarity 0.89)
- Learning View Priors for Single-View 3D Reconstruction (CVPR 2019 · similarity 0.89)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.87)
- Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses (NeurIPS 2024 · similarity 0.87)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.87)
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.