中文
相关论文

相关论文: One Model to Rig Them All: Diverse Skeleton Riggin…

200 篇论文

Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including cross-modal and multi-modal scenarios. However, their direct application to 3D human…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Siyuan Yang , Jun Liu , Hao Cheng , Chong Wang , Shijian Lu , Hedvig Kjellstrom , Weisi Lin , Alex C. Kot

Recent research efforts have yielded significant advancements in manipulating objects under homogeneous settings where the robot is required to either manipulate rigid or deformable (soft) objects. However, the manipulation under…

机器人学 · 计算机科学 2025-02-11 Zixing Wang , Ahmed H. Qureshi

Secondary animation effects are essential for liveliness. We propose a simple, real-time solution for adding them on top of standard skinning, enabling artist-driven stylization of skeletal motion. Our method takes a standard skeleton…

Quantifying axon and myelin properties (e.g., axon diameter, myelin thickness, g-ratio) in histology images can provide useful information about microstructural changes caused by neurodegenerative diseases. Automatic tissue segmentation is…

图像与视频处理 · 电气工程与系统科学 2024-09-19 Armand Collin , Arthur Boschet , Mathieu Boudreau , Julien Cohen-Adad

The growing complexity and scale of visual model pre-training have made developing and deploying multi-task computer-aided diagnosis (CAD) systems increasingly challenging and resource-intensive. Furthermore, the medical imaging community…

计算机视觉与模式识别 · 计算机科学 2025-05-16 Yitao Zhu , Yuan Yin , Zhenrong Shen , Zihao Zhao , Haiyu Song , Sheng Wang , Dinggang Shen , Qian Wang

Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) face two critical challenges: the lack of cross-image reasoning…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Lihao Zheng , Jiawei Chen , Xintian Shen , Hao Ma , Tao Wei

Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminative or prompt-based methods largely rely on appearance correlations and provide limited…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Hongrui Li , Yichen Shi , Hongyang Wang , Yuhao Gao , Hui Ma , Jun Feng , Zitong Yu

The integration of large language models (LLMs) into robotic systems has accelerated progress in embodied artificial intelligence, yet current approaches remain constrained by existing robotic architectures, particularly serial mechanisms.…

机器人学 · 计算机科学 2025-10-07 Guanglu Jia , Ceng Zhang , Gregory S. Chirikjian

Machine learning-based surrogate models have emerged as a powerful tool to accelerate simulation-driven scientific workflows, but their adoption is limited by the lack of large-scale, diverse, and standardized datasets for physics-based…

Achieving autonomous and versatile whole-body loco-manipulation remains a central barrier to making humanoids practically useful. Yet existing approaches are fundamentally constrained: retargeted data are often scarce or low-quality;…

机器人学 · 计算机科学 2026-03-04 Xialin He , Sirui Xu , Xinyao Li , Runpei Dong , Liuyu Bian , Yu-Xiong Wang , Liang-Yan Gui

Incremental gradient (IG) methods, such as stochastic gradient descent and its variants are commonly used for large scale optimization in machine learning. Despite the sustained effort to make IG methods more data-efficient, it remains an…

机器学习 · 计算机科学 2020-11-18 Baharan Mirzasoleiman , Jeff Bilmes , Jure Leskovec

In this paper, we address the challenge of reconstructing general articulated 3D objects from a single video. Existing works employing dynamic neural radiance fields have advanced the modeling of articulated objects like humans and animals…

计算机视觉与模式识别 · 计算机科学 2024-04-18 Chaoyue Song , Jiacheng Wei , Chuan-Sheng Foo , Guosheng Lin , Fayao Liu

Machine unlearning methods aim to remove sensitive or unwanted content from trained models, but typically demand extensive model updates at significant computational cost while potentially degrading model performance on both related and…

机器学习 · 计算机科学 2025-06-02 Zikui Cai , Yaoteng Tan , M. Salman Asif

While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced when facing new…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Zongye Zhang , Wenrui Cai , Qingjie Liu , Yunhong Wang

Generative recommendation has recently emerged as a transformative paradigm that directly generates target items, surpassing traditional cascaded approaches. It typically involves two components: a tokenizer that learns item identifiers and…

In this paper, we aim at solving pixel-wise binary problems, including salient object segmentation, skeleton extraction, and edge detection, by introducing a unified architecture. Previous works have proposed tailored methods for solving…

计算机视觉与模式识别 · 计算机科学 2019-04-09 Qibin Hou , Jiang-Jiang Liu , Ming-Ming Cheng , Ali Borji , Philip H. S. Torr

Generating or editing images directly from Neural signals has immense potential at the intersection of neuroscience, vision, and Brain-computer interaction. In this paper, We present Uni-Neur2Img, a unified framework for neural…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Xiyue Bai , Ronghao Yu , Jia Xiu , Pengfei Zhou , Jie Xia , Peng Ji

Visual generative and understanding models typically rely on distinct tokenizers to process images, presenting a key challenge for unifying them within a single framework. Recent studies attempt to address this by connecting the training of…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Chuofan Ma , Yi Jiang , Junfeng Wu , Jihan Yang , Xin Yu , Zehuan Yuan , Bingyue Peng , Xiaojuan Qi

We present CharacterMixer, a system for blending two rigged 3D characters with different mesh and skeleton topologies while maintaining a rig throughout interpolation. CharacterMixer also enables interpolation during motion for such…

图形学 · 计算机科学 2024-02-27 Xiao Zhan , Rao Fu , Daniel Ritchie

Large-scale controllable 3D assets are critical for computer graphics, embodied AI, robotics, and interactive content creation, yet creating diverse 3D assets remains challenging due to the high cost of manual modeling and rigging. Shape…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Yumeng He , Xiaoying Wang , Peihao Li , Yanjia Huang , Joe Masterjohn , Jiajun Wu , Leonidas Guibas , Yin Yang , Ying Jiang , Chenfanfu Jiang