English
Related papers

Related papers: D3PRefiner: A Diffusion-based Denoise Method for 3…

200 papers

Single-view 3D human reconstruction has achieved remarkable progress through the adoption of multi-view diffusion models, yet the recovered 3D humans often exhibit unnatural poses. This phenomenon becomes pronounced when reconstructing 3D…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Seunguk Do , Minwoo Huh , Joonghyuk Shin , Jaesik Park

3D human pose estimation from monocular images is a highly ill-posed problem due to depth ambiguities and occlusions. Nonetheless, most existing works ignore these ambiguities and only estimate a single solution. In contrast, we generate a…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Tom Wehrbein , Marco Rudolph , Bodo Rosenhahn , Bastian Wandt

Motion capture from a limited number of body-worn sensors, such as inertial measurement units (IMUs) and pressure insoles, has important applications in health, human performance, and entertainment. Recent work has focused on accurately…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Tom Van Wouwe , Seunghwan Lee , Antoine Falisse , Scott Delp , C. Karen Liu

Monocular depth estimation is a challenging task that predicts the pixel-wise depth from a single 2D image. Current methods typically model this problem as a regression or classification task. We propose DiffusionDepth, a new approach that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-30 Yiqun Duan , Xianda Guo , Zheng Zhu

3D human pose estimation from a single image is still a challenging problem despite the large amount of work that has been performed in this field. Generally, most methods directly use neural networks and ignore certain constraints (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Yicheng Deng , Cheng Sun , Yongqi Sun , Jiahui Zhu

Monocular 3D pose estimation is fundamentally ill-posed due to depth ambiguity and occlusions, thereby motivating probabilistic methods that generate multiple plausible 3D pose hypotheses. In particular, diffusion-based models have recently…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Ti Wang , Xiaohang Yu , Mackenzie Weygandt Mathis

Full 3D estimation of human pose from a single image remains a challenging task despite many recent advances. In this paper, we explore the hypothesis that strong prior information about scene geometry can be used to improve pose estimation…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Zhe Wang , Liyan Chen , Shaurya Rathore , Daeyun Shin , Charless Fowlkes

In this paper, we introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D registration task as a denoising diffusion process, which…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Haobo Jiang , Mathieu Salzmann , Zheng Dang , Jin Xie , Jian Yang

To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augmentation techniques are limited to the "seen" pose combinations…

Computer Vision and Pattern Recognition · Computer Science 2023-01-10 Cheng-Yen Yang , Jiajia Luo , Lu Xia , Yuyin Sun , Nan Qiao , Ke Zhang , Zhongyu Jiang , Jenq-Neng Hwang

We introduce UPose3D, a novel approach for multi-view 3D human pose estimation, addressing challenges in accuracy and scalability. Our method advances existing pose estimation frameworks by improving robustness and flexibility without…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Vandad Davoodnia , Saeed Ghorbani , Marc-André Carbonneau , Alexandre Messier , Ali Etemad

Monocular 3D human pose and shape estimation is an inherently ill-posed problem due to depth ambiguities, occlusions, and truncations. Recent probabilistic approaches learn a distribution over plausible 3D human meshes by maximizing the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Tom Wehrbein , Marco Rudolph , Bodo Rosenhahn , Bastian Wandt

Deterministic models for 3D hand pose reconstruction, whether single-staged or cascaded, struggle with pose ambiguities caused by self-occlusions and complex hand articulations. Existing cascaded approaches refine predictions in a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Taeyun Woo , Jinah Park , Tae-Kyun Kim

The availability of the large-scale labeled 3D poses in the Human3.6M dataset plays an important role in advancing the algorithms for 3D human pose estimation from a still image. We observe that recent innovation in this area mainly focuses…

Computer Vision and Pattern Recognition · Computer Science 2019-04-12 Luyang Wang , Yan Chen , Zhenhua Guo , Keyuan Qian , Mude Lin , Hongsheng Li , Jimmy S. Ren

Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent success of the diffusion probabilistic model (DPM), we…

Computer Vision and Pattern Recognition · Computer Science 2024-01-10 Yunfan Ye , Kai Xu , Yuhang Huang , Renjiao Yi , Zhiping Cai

The accuracy and robustness of 3D human pose estimation (HPE) are limited by 2D pose detection errors and 2D to 3D ill-posed challenges, which have drawn great attention to Multi-Hypothesis HPE research. Most existing MH-HPE methods are…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Xianzhou Zeng , Hao Qin , Ming Kong , Luyuan Chen , Qiang Zhu

Estimating 2D-3D correspondences between RGB images and 3D space is a fundamental problem in 6D object pose estimation. Recent pose estimators use dense correspondence maps and Point-to-Point algorithms to estimate object poses. The…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Peter Hönig , Stefan Thalhammer , Markus Vincze

3D human pose data collected in controlled laboratory settings present challenges for pose estimators that generalize across diverse scenarios. To address this, domain generalization is employed. Current methodologies in domain…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Qucheng Peng , Ce Zheng , Chen Chen

Following the successful application of deep convolutional neural networks to 2d human pose estimation, the next logical problem to solve is 3d human pose estimation from monocular images. While previous solutions have shown some success,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-04 Alec Diaz-Arias , Mitchell Messmore , Dmitriy Shin , Stephen Baek

Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achieve absolute 3D human…

Computer Vision and Pattern Recognition · Computer Science 2022-05-18 Guoliang Hua , Hong Liu , Wenhao Li , Qian Zhang , Runwei Ding , Xin Xu

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…

Computer Vision and Pattern Recognition · Computer Science 2016-07-27 Albert Haque , Boya Peng , Zelun Luo , Alexandre Alahi , Serena Yeung , Li Fei-Fei