Mv-reid: 3d multi-view transformation network for occluded person re-identification

Z Yu, P Tiwari, L Hou, L Li, W Li, L Jiang… - Knowledge-Based Systems, 2024 - Elsevier
Re-identification (ReID) of occluded persons is a challenging task due to the loss of
information in scenes with occlusions. Most existing methods for occluded ReID use 2D …

Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling

H Ji, H Deng, Y Dai, H Li - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
Most existing 3D human pose estimation work rely heavily on the powerful memory
capability of networks to obtain suitable 2D-3D map**s from the training data. Few works …

Recent Trends in 3D Reconstruction of General Non‐Rigid Scenes

R Yunus, JE Lenssen, M Niemeyer… - Computer Graphics …, 2024 - Wiley Online Library
Reconstructing models of the real world, including 3D geometry, appearance, and motion of
real scenes, is essential for computer graphics and computer vision. It enables the …

3D-LFM: Lifting Foundation Model

M Dabhi, LA Jeni, S Lucey - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
The lifting of a 3D structure and camera from 2D landmarks is at the cornerstone of the
discipline of computer vision. Traditional methods have been confined to specific rigid …

Unsupervised 3D Structure Inference from Category-Specific Image Collections

W Wang, D Cao, F Bernard - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
Understanding 3D object structure from image collections of general object categories
remains a long-standing challenge in computer vision. Due to the high relevance of image …

Non-rigid Structure-from-Motion: Temporally-smooth Procrustean Alignment and Spatially-variant Deformation Modeling

J Shi, H Deng, Y Dai - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Abstract Even though Non-rigid Structure-from-Motion (NRSfM) has been extensively
studied and great progress has been made there are still key challenges that hinder their …

3D Human Pose Analysis via Diffusion Synthesis

H Ji, H Li - arxiv preprint arxiv:2401.08930, 2024 - arxiv.org
Diffusion models have demonstrated remarkable success in generative modeling. In this
paper, we propose PADS (Pose Analysis by Diffusion Synthesis), a novel framework …