Research map / 3D vision / Face and shape
Online Adaptation for Consistent Mesh Reconstruction in the Wild
Xueting Li, Sifei Liu, Shalini De Mello, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, Jan Kautz
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 motion deformation branch (asymmetric dV) (ablation) | ACMR · CUB test (image) | Mask IoU: 0.647 -> 0.708 | Improved |
| add motion deformation branch (asymmetric dV) (ablation) | ACMR · CUB test (image) | PCK@0.1: 0.790 -> 0.855 | Improved |
| add ARAP constraint in image training (ablation) | ACMR · CUB test (image) | Mask IoU: 0.758 -> 0.708 | Hurt |
| add ARAP constraint in image training (ablation) | ACMR · CUB test (image) | PCK@0.1: 0.857 -> 0.855 | No clear effect |
| use 8 shape bases instead of a single template (ablation) | ACMR · CUB test (image) | Mask IoU: 0.605 -> 0.708 | Improved |
| use 8 shape bases instead of a single template (ablation) | ACMR · CUB test (image) | PCK@0.1: 0.655 -> 0.855 | Improved |
| asymmetric shape with bases and ARAP (ACMR) vs CMR | CMR baseline · CUB test (image) | PCK@0.1: 0.810 -> 0.855 | Improved |
| switch encoder to ResNet50 with group norm (ACMR-vid) | ACMR · CUB test (image) | Mask IoU: 0.708 -> 0.773 | Improved |
| test-time tuning ResNet18 BN model on video (ablation) | ACMR · Bird video dataset | PCK@0.1: 0.751 -> 0.424 | Hurt |
| online adaptation on test video (no invariance losses) (ablation) | ACMR-vid · Bird video dataset | J mean: 0.686 -> 0.836 | Improved |
| add part, texture, base shape invariance losses in online adaptation (ablation) | ACMR-vid (T) · Bird video dataset | F mean: 0.666 -> 0.756 | Improved |
| add part, texture, base shape invariance losses in online adaptation (ablation) | ACMR-vid (T) · Bird video dataset | PCK@0.1: 0.644 -> 0.794 | Improved |
Closest papers by meaning
- Self-supervised Single-view 3D Reconstruction via Semantic Consistency (ECCV 2020 · similarity 0.90)
- Distilling Neural Fields for Real-Time Articulated Shape Reconstruction (CVPR 2023 · similarity 0.89)
- Learning Monocular 3D Reconstruction of Articulated Categories From Motion (CVPR 2021 · similarity 0.89)
- SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · similarity 0.87)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.87)
- Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video (NeurIPS 2025 · 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.
