paper-with-me

홈 › Papers

PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation

2023-08-18 · Hanbing Liu, Jun-Yan He, Zhi-Qi Cheng, Wangmeng Xiang, Qize Yang, Wenhao Chai, Gaoang Wang, Xu Bao, Bin Luo, Yifeng Geng, Xuansong Xie

Existing 3D human pose estimators face challenges in adapting to new datasets due to the lack of 2D-3D pose pairs in training sets. To overcome this issue, we propose \textit{Multi-Hypothesis \textbf{P}ose \textbf{Syn}thesis \textbf{D}omain \textbf{A}daptation} (\textbf{PoSynDA}) framework to bridge this data disparity gap in target domain. Typically, PoSynDA uses a diffusion-inspired structure to simulate 3D pose distribution in the target domain. By incorporating a multi-hypothesis network, PoSynDA generates diverse pose hypotheses and aligns them with the target domain. To do this, it first utilizes target-specific source augmentation to obtain the target domain distribution data from the source domain by decoupling the scale and position parameters. The process is then further refined through the teacher-student paradigm and low-rank adaptation. With extensive comparison of benchmarks such as Human3.6M and MPI-INF-3DHP, PoSynDA demonstrates competitive performance, even comparable to the target-trained MixSTE model\cite{zhang2022mixste}. This work paves the way for the practical application of 3D human pose estimation in unseen domains. The code is available at https://github.com/hbing-l/PoSynDA.

📄 PDF Abstract BibTeX arXiv:2308.09678

Code (1)

hbing-l/posynda 공식 구현 pytorch

Tasks

3D Human Pose EstimationDomain AdaptationPose Estimation

Similar Papers 제목 키워드 기반

Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach

2023-02-23 · Minyoung Kim, Da Li, Timothy Hospedales

We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving…

Domain Adaptation

Learning logic programs by discovering where not to search

2022-02-20 · Andrew Cropper, Céline Hocquette

The goal of inductive logic programming (ILP) is to search for a hypothesis that generalises training examples and background knowledge (BK). To improve performance, we introduce an approach that, before searching for a …

Inductive logic programmingProgram Synthesis

Mechanisms of Matter: Language Inferential Benchmark on Physicochemical Hypothesis in Materials Synthesis

2025-09-29 · Yingming Pu, Tao Lin, Hongyu Chen arxiv

The capacity of Large Language Models (LLMs) to generate valid scientific hypotheses for materials synthesis remains largely unquantified, hindered by the absence of benchmarks probing physicochemical logics reasoning. T…

Computational Efficiency

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

2019-12-11 · CVPR 2020 6 · Yiyi Liao, Katja Schwarz, Lars Mescheder, Andreas Geiger

In recent years, Generative Adversarial Networks have achieved impressive results in photorealistic image synthesis. This progress nurtures hopes that one day the classical rendering pipeline can be replaced by efficient…

Image GenerationObject

Parallel Constraint-Driven Inductive Logic Programming

2021-09-15 · Andrew Cropper, Oghenejokpeme Orhobor, Cristian Dinu, Rolf Morel

Multi-core machines are ubiquitous. However, most inductive logic programming (ILP) approaches use only a single core, which severely limits their scalability. To address this limitation, we introduce parallel techniques…

Inductive logic programmingProgram Synthesis