paper-with-me

Papers

HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation

2025-08-20 · Bing Han, Yuhua Huang, Pan Gao arxiv

Monocular 3D human pose estimation (HPE) often encounters challenges such as depth ambiguity and occlusion during the 2D-to-3D lifting process. Additionally, traditional methods may overlook multi-scale skeleton features when utilizing skeleton structure information, which can negatively impact the accuracy of pose estimation. To address these challenges, this paper introduces a novel 3D pose estimation method, HyperDiff, which integrates diffusion models with HyperGCN. The diffusion model effectively captures data uncertainty, alleviating depth ambiguity and occlusion. Meanwhile, HyperGCN, serving as a denoiser, employs multi-granularity structures to accurately model high-order correlations between joints. This improves the model's denoising capability especially for complex poses. Experimental results demonstrate that HyperDiff achieves state-of-the-art performance on the Human3.6M and MPI-INF-3DHP datasets and can flexibly adapt to varying computational resources to balance performance and efficiency.

📄 PDF Abstract BibTeX arXiv:2508.14431

Code (0)

등록된 구현이 없습니다.

Tasks

Monocular 3D Human Pose Estimation3D Pose Estimation

Similar Papers 제목 키워드 기반

HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion

2023-03-29 · ICCV 2023 1 · Ziya Erkoç, Fangchang Ma, Qi Shan, Matthias Nießner 외

Implicit neural fields, typically encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to signals (e.g., signed distances), have shown remarkable promise as a high-fidelity and compact represen…

HyperDiffusionFields (HyDiF): Diffusion-Guided Hypernetworks for Learning Implicit Molecular Neural Fields

2025-10-20 · Sudarshan Babu, Phillip Lo, Xiao Zhang, Aadi Srivastava 외 arxiv

We introduce HyperDiffusionFields (HyDiF), a framework that models 3D molecular conformers as continuous fields rather than discrete atomic coordinates or graphs. At the core of our approach is the Molecular Directional …

Molecular Property Prediction

Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach

2026-03-16 · Mengyao Zhou, Zhiheng Zhou, Xiao Han, Xingqin Qi 외 arxiv

Hypergraph neural networks (HGNNs) have demonstrated strong capabilities in modeling complex higher-order relationships. However, existing HGNNs often suffer from over-smoothing as the number of layers increases and lack…

Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing

2026-04-13 · Zhiheng Zhou, Mengyao Zhou, Xixun Lin, Xingqin Qi 외 arxiv

Hypergraph neural networks (HGNNs) have shown remarkable potential in modeling high-order relationships that naturally arise in many real-world data domains. However, existing HGNNs often suffer from shallow propagation,…

From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks

2026-07-17 · Zhiheng Zhou, Mengyao Zhou, Yancheng Chen, Dengyi Zhao 외 arxiv

Higher-order couplings enhance the expressive power of hypergraph neural networks (HGNNs), but they also intensify representation collapse in deep propagation due to strong multi-way feature mixing. This work investigate…