Arbitrary 发表于 2025-3-28 17:22:43

Weakly-Supervised Reconstruction of 3D Objects with Large Shape Variation from Single In-the-Wild Imave distracting background. This paper proposes a novel learning framework for reconstructing 3D objects with large shape variation from single in-the-wild images. Considering that shape variation leads to appearance change of objects at various scales, we propose a fusion module to form combined mu

含沙射影 发表于 2025-3-28 20:16:40

HPGCNN: Hierarchical Parallel Group Convolutional Neural Networks for Point Clouds Processinge key component in our approach is the Hierarchical Parallel Group Convolution (HPGConv) operation. It can capture both the discriminative independent single-point features and local geometric features of point clouds at the same time to enhance the richness of the features with less redundant infor

JEER 发表于 2025-3-29 02:00:28

http://reply.papertrans.cn/24/2342/234131/234131_43.png

interior 发表于 2025-3-29 05:19:09

Reconstructing Creative Lego Modelsing creativity. In this paper, from a set of 2D input images, we create a monolithic mesh, representing a physical 3D Lego model as input, and split it in to its known components such that the output of the program can be used to completely reconstruct the input model, brick for brick. We present a

convert 发表于 2025-3-29 08:35:39

http://reply.papertrans.cn/24/2342/234131/234131_45.png

ineluctable 发表于 2025-3-29 14:03:59

Learning Global Pose Features in Graph Convolutional Networks for 3D Human Pose Estimation body structure for 3D human pose estimation (HPE). However, a vanilla graph convolutional layer, the building block of a GCN, only models the local relationships between each body joint and their neighbors on the skeleton graph. Some global attributes, e.g., the action of the person, can be critica

门闩 发表于 2025-3-29 19:21:12

SGNet: Semantics Guided Deep Stereo Matchingears. Despite of great progress, it’s still challenging to achieve high accurate disparity map due to low texture and illumination changes in the scene. High-level semantic information can be helpful to handle these problems. In this paper a deep semantics guided stereo matching network (SGNet) is p

夸张 发表于 2025-3-29 22:26:48

Reconstructing Human Body Mesh from Point Clouds by Adversarial GP Networkaches for shape matching that rely on Deep Neural Networks (DNNs) achieve state-of-the-art results with generic point-wise architectures; but in doing so, they exploit much weaker human body shape and surface priors with respect to methods that explicitly model the body surface with 3D templates. We

得意牛 发表于 2025-3-30 00:31:07

http://reply.papertrans.cn/24/2342/234131/234131_49.png

渗入 发表于 2025-3-30 05:55:10

http://reply.papertrans.cn/24/2342/234131/234131_50.png
页: 1 2 3 4 [5] 6 7
查看完整版本: Titlebook: Computer Vision – ACCV 2020; 15th Asian Conferenc Hiroshi Ishikawa,Cheng-Lin Liu,Jianbo Shi Conference proceedings 2021 Springer Nature Swi