Research map / 3D vision / Face and shape
3D Congealing: 3D-Aware Image Alignment in the Wild
Yunzhi Zhang, Zizhang Li, Amit Raj, Andreas Engelhardt, Yuanzhen Li, Tingbo Hou, Jiajun Wu, Varun Jampani
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 analysis-by-synthesis pose initialization (exhaustive FoV/azimuth/elevation candidates) (ablation) | 3D Congealing · NAVI in-the-wild (S_C) | rotation error (deg): 53.45 -> 26.97 | Improved |
| add IoU-loss pose refinement after initialization (ablation) | 3D Congealing · NAVI in-the-wild (S_C) | rotation error (deg): 31.29 -> 26.97 | Improved |
| add IoU-loss pose refinement (ablation) | 3D Congealing · NAVI in-the-wild (COLMAP-failing scenes) | rotation error (deg): 31.15 -> 32.56 (refinement lowers translation error 0.85 -> 0.41) | Improved |
| use semantic-feature, generative-prior pose estimation versus photometric baselines GNeRF and PoseDiffusion | 3D Congealing · NAVI in-the-wild (S_C) | rotation error (deg): 93.15 (GNeRF) / 46.79 (PoseDiffusion) -> 26.97 | Improved |
| use 3D canonical-shape correspondence instead of direct 2D DINOv2 feature matching | 3D Congealing · SPair-71k (9 rigid categories) | PCK@0.1 mean: 55.0 -> 57.2 | Improved |
| use 3D congealing correspondence on trains versus 2D matching | 3D Congealing · SPair-71k (Train category) | PCK@0.1: 53.5 -> 26.1 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PoseDiffusion — PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment (ICCV 2023) · better on 3 of 3 shared results
- GNeRF — GNeRF: GAN-Based Neural Radiance Field Without Posed Camera (ICCV 2021) · better on 2 of 2 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
- Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence (NeurIPS 2026 · similarity 0.87)
- SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations (CVPR 2025 · similarity 0.87)
- One-shot 3D Object Canonicalization based on Geometric and Semantic Consistency (CVPR 2025 · similarity 0.87)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.85)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.85)
- MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image (CVPR 2025 · 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.
