Semantics-aware Test-time Adaptation for 3D Human Pose Estimation

2025-02-15 · Qiuxia Lin, Rongyu Chen, Kerui Gu, Angela Yao

This work highlights a semantics misalignment in 3D human pose estimation. For the task of test-time adaptation, the misalignment manifests as overly smoothed and unguided predictions. The smoothing settles predictions towards some average pose. Furthermore, when there are occlusions or truncations, the adaptation becomes fully unguided. To this end, we pioneer the integration of a semantics-aware motion prior for the test-time adaptation of 3D pose estimation. We leverage video understanding and a well-structured motion-text space to adapt the model motion prediction to adhere to video semantics during test time. Additionally, we incorporate a missing 2D pose completion based on the motion-text similarity. The pose completion strengthens the motion prior's guidance for occlusions and truncations. Our method significantly improves state-of-the-art 3D human pose estimation TTA techniques, with more than 12% decrease in PA-MPJPE on 3DPW and 3DHP.

📄 PDF Abstract BibTeX arXiv:2502.10724

Code (0)

등록된 구현이 없습니다.

Tasks

3D human pose and shape estimation 3D Human Pose Estimation 3D Pose Estimationmotion predictionPose Estimation Test-time Adaptationtext similarityVideo Understanding

Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs

2026-08-28 · Bo Li, Xin Zheng, Ming Jin, Can Wang 외 arxiv

Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which involves potential distribution shifts that may harm model generalizatio…

Test-time Adaptation Graph Neural Network

CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher

2025-12-20 · Tianlun Liu, Zhiliang Tian, Zhen Huang, Xingzhi Zhou 외 arxiv

Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), …

Test-time Adaptation Domain Adaptation

Fast Adaptation for Human Pose Estimation via Meta-Optimization

2024-01-01 · CVPR 2024 1 · Shengxiang Hu, Huaijiang Sun, Bin Li, Dong Wei 외

Domain shift is a challenge for supervised human pose estimation where the source data and target data come from different distributions. This is why pose estimation methods generally perform worse on the test set th…

Auxiliary Learning Image Inpainting Meta-Learning Pose Estimation+2

Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift

2026-04-27 · Lixian Chen, Yanhui Chen, Junyi Lin arxiv

Vision-language models transfer well in zero-shot settings, but at deployment the visual and textual branches often shift asymmetrically. Under this condition, entropy-based test-time adaptation can sharpen the fused pos…

Test-time Adaptation

SAM-aware Test-time Adaptation for Universal Medical Image Segmentation

2025-06-05 · Jianghao Wu, Yicheng Wu, Yutong Xie, Wenjia Bai 외

Universal medical image segmentation using the Segment Anything Model (SAM) remains challenging due to its limited adaptability to medical domains. Existing adaptations, such as MedSAM, enhance SAM's performance in medic…

Image Segmentation Medical Image Segmentation Semantic Segmentation Test-time Adaptation