ELUC
发表于 2025-3-28 17:16:18
http://reply.papertrans.cn/24/2343/234218/234218_41.png
头脑冷静
发表于 2025-3-28 21:34:21
http://reply.papertrans.cn/24/2343/234218/234218_42.png
dagger
发表于 2025-3-29 01:16:58
Cyclic Functional Mapping: Self-supervised Correspondence Between Non-isometric Deformable Shapes,k of alignment in non-Euclidean domains is one of the most fundamental and crucial problems in computer vision. As 3D scanners can generate highly complex and dense models, the mission of finding dense mappings between those models is vital. The novelty of our solution is based on a cyclic mapping b
hypotension
发表于 2025-3-29 05:48:13
http://reply.papertrans.cn/24/2343/234218/234218_44.png
愉快么
发表于 2025-3-29 08:18:01
Contact and Human Dynamics from Monocular Video,nstraints, such as feet penetrating the ground and bodies leaning at extreme angles. In this paper, we present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input. We first estimate ground contact timings with a novel predict
dura-mater
发表于 2025-3-29 15:03:34
PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation,-to-fine fashion. Flow computed at the coarse level is upsampled and warped to a finer level, enabling the algorithm to accommodate for large motion without a prohibitive search space. We introduce novel cost volume, upsampling, and warping layers to efficiently handle 3D point cloud data. Unlike tr
得罪
发表于 2025-3-29 19:25:58
Learning Implicit Surfaces from Point Clouds,ction) start to degrade in the presence of noisy and partial scans. Hence, deep learning based methods have recently been proposed to produce complete surfaces, even from partial scans. However, such data-driven methods struggle to generalize to new shapes with large geometric and topological variat
lymphoma
发表于 2025-3-29 22:08:46
http://reply.papertrans.cn/24/2343/234218/234218_48.png
不如乐死去
发表于 2025-3-30 03:06:19
Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting,d modeling capacity and fail to generalize well to in-the-wild data. Use of deformation transfer or multilinear tensor as a personalized 3DMM for blendshape interpolation does not address the fact that facial expressions result in different local and global skin deformations in different persons. Mo
acheon
发表于 2025-3-30 07:30:15
http://reply.papertrans.cn/24/2343/234218/234218_50.png