中文
相关论文

相关论文: FG-MDM: Towards Zero-Shot Human Motion Generation …

200 篇论文

We present Dynamics-Guided Diffusion Model (DGDM), a data-driven framework for generating task-specific manipulator designs without task-specific training. Given object shapes and task specifications, DGDM generates sensor-less manipulator…

机器人学 · 计算机科学 2025-03-31 Xiaomeng Xu , Huy Ha , Shuran Song

Recent works have sought to enhance the controllability and precision of text-driven motion generation. Some approaches leverage large language models (LLMs) to produce more detailed texts, while others incorporate global 3D coordinate…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Keming Shen , Bizhu Wu , Junliang Chen , Xiaoqin Wang , Linlin Shen

This work introduces the generative fractional diffusion model for protein generation (ProT-GFDM), a novel generative framework that employs fractional stochastic dynamics for protein backbone structure modeling. This approach builds on the…

定量方法 · 定量生物学 2025-05-01 Xiao Liang , Wentao Ma , Eric Paquet , Herna Lydia Viktor , Wojtek Michalowski

Human motion generation from text prompts has made remarkable progress in recent years. However, existing methods primarily rely on either sequence-level or action-level descriptions due to the absence of fine-grained, part-level motion…

计算机视觉与模式识别 · 计算机科学 2026-01-19 Chuqiao Li , Xianghui Xie , Yong Cao , Andreas Geiger , Gerard Pons-Moll

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Ning Zhang , Zhengyu Li , Kwong Weng Loh , Mingxi Xu , Qi Wang , Zhengyu Wen , Xiaoyu He , Wei Zhao , Kehong Gong , Mingyuan Zhang

Generating 3D human motions from textual descriptions is an important research problem with broad applications in video games, virtual reality, and augmented reality. Recent methods align the textual description with human motion at the…

计算机视觉与模式识别 · 计算机科学 2025-12-25 Bowen Dang , Lin Wu , Xiaohang Yang , Zheng Yuan , Zhixiang Chen

Text-to-motion generation requires not only grounding local actions in language but also seamlessly blending these individual actions to synthesize diverse and realistic global motions. However, existing motion generation methods primarily…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Peng Jin , Hao Li , Zesen Cheng , Kehan Li , Runyi Yu , Chang Liu , Xiangyang Ji , Li Yuan , Jie Chen

Despite advancements in Multimodal Large Language Models (MLLMs), their proficiency in fine-grained video motion understanding remains critically limited. They often lack inter-frame differencing and tend to average or ignore subtle visual…

计算机视觉与模式识别 · 计算机科学 2025-10-10 Yipeng Du , Tiehan Fan , Kepan Nan , Rui Xie , Penghao Zhou , Xiang Li , Jian Yang , Zhenheng Yang , Ying Tai

In this paper, we propose a unified framework that leverages a single pretrained LLM for Motion-related Multimodal Generation, referred to as MoMug. MoMug integrates diffusion-based continuous motion generation with the model's inherent…

机器学习 · 计算机科学 2025-03-11 Shinichi Tanaka , Zhao Wang , Yoichi Kato , Jun Ohya

Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation.…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Vincent Tao Hu , Wenzhe Yin , Pingchuan Ma , Yunlu Chen , Basura Fernando , Yuki M Asano , Efstratios Gavves , Pascal Mettes , Bjorn Ommer , Cees G. M. Snoek

Sign language videos are an important medium for spreading and learning sign language. However, most existing human image synthesis methods produce sign language images with details that are distorted, blurred, or structurally incorrect.…

计算机视觉与模式识别 · 计算机科学 2024-09-26 Tongkai Shi , Lianyu Hu , Fanhua Shang , Jichao Feng , Peidong Liu , Wei Feng

Text-conditioned motion synthesis has made remarkable progress with the emergence of diffusion models. However, the majority of these motion diffusion models are primarily designed for a single character and overlook multi-human…

计算机视觉与模式识别 · 计算机科学 2024-11-22 Zhenzhi Wang , Jingbo Wang , Yixuan Li , Dahua Lin , Bo Dai

Our paper aims to generate diverse and realistic animal motion sequences from textual descriptions, without a large-scale animal text-motion dataset. While the task of text-driven human motion synthesis is already extensively studied and…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Zhangsihao Yang , Mingyuan Zhou , Mengyi Shan , Bingbing Wen , Ziwei Xuan , Mitch Hill , Junjie Bai , Guo-Jun Qi , Yalin Wang

While recent advances in text-to-motion generation have shown promising results, they typically assume all individuals are grouped as a single unit. Scaling these methods to handle larger crowds and ensuring that individuals respond…

计算机视觉与模式识别 · 计算机科学 2025-05-12 Yukang Cao , Xinying Guo , Mingyuan Zhang , Haozhe Xie , Chenyang Gu , Ziwei Liu

Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Ryugo Morita , Stanislav Frolov , Brian Bernhard Moser , Takahiro Shirakawa , Ko Watanabe , Andreas Dengel , Jinjia Zhou

Generating human motion that satisfies customized zero-shot goal functions, enabling applications such as controllable character animation and behavior synthesis for virtual agents, is a critical capability. While current approaches handle…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Hanchao Liu , Fang-Lue Zhang , Shining Zhang , Tai-Jiang Mu , Shi-Min Hu

While many diffusion models perform well when controlling particular aspects such as style, character, and interaction, they struggle with fine-grained control due to dataset limitations and intricate model architecture design. This paper…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Conghan Yue , Zhengwei Peng , Shiyan Du , Zhi Ji , Chuangjian Cai , Le Wan , Dongyu Zhang

Diffusion models (DMs) have been adopted across diverse fields with its remarkable abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a stochastic…

计算机视觉与模式识别 · 计算机科学 2023-10-05 Zike Wu , Pan Zhou , Kenji Kawaguchi , Hanwang Zhang

Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Qing Yu , Akihisa Watanabe , Kent Fujiwara

Text-guided human motion generation has drawn significant interest because of its impactful applications spanning animation and robotics. Recently, application of diffusion models for motion generation has enabled improvements in the…

计算机视觉与模式识别 · 计算机科学 2023-05-17 Samaneh Azadi , Akbar Shah , Thomas Hayes , Devi Parikh , Sonal Gupta