中文
相关论文

相关论文: DreamActor-H1: High-Fidelity Human-Product Demonst…

200 篇论文

Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly…

计算机视觉与模式识别 · 计算机科学 2025-12-29 Shen Zheng , Jiaran Cai , Yuansheng Guan , Shenneng Huang , Xingpei Ma , Junjie Cao , Hanfeng Zhao , Qiang Zhang , Shunsi Zhang , Xiao-Ping Zhang

While recent image-based human animation methods achieve realistic body and facial motion synthesis, critical gaps remain in fine-grained holistic controllability, multi-scale adaptability, and long-term temporal coherence, which leads to…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Yuxuan Luo , Zhengkun Rong , Lizhen Wang , Longhao Zhang , Tianshu Hu , Yongming Zhu

We present a novel approach for generating 360-degree high-quality, spatio-temporally coherent human videos from a single image. Our framework combines the strengths of diffusion transformers for capturing global correlations across…

计算机视觉与模式识别 · 计算机科学 2024-09-25 Ruizhi Shao , Youxin Pang , Zerong Zheng , Jingxiang Sun , Yebin Liu

Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Qijun Gan , Yi Ren , Chen Zhang , Zhenhui Ye , Pan Xie , Xiang Yin , Zehuan Yuan , Bingyue Peng , Jianke Zhu

Video virtual try-on (VVT) technology has garnered considerable academic interest owing to its promising applications in e-commerce advertising and entertainment. However, most existing end-to-end methods rely heavily on scarce paired…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Tongchun Zuo , Zaiyu Huang , Shuliang Ning , Ente Lin , Chao Liang , Zerong Zheng , Jianwen Jiang , Yuan Zhang , Mingyuan Gao , Xin Dong

High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Minh Khoa Le , Kien Do , Duc Thanh Nguyen , Truyen Tran

Video try-on stands as a promising area for its tremendous real-world potential. Prior works are limited to transferring product clothing images onto person videos with simple poses and backgrounds, while underperforming on casually…

计算机视觉与模式识别 · 计算机科学 2024-06-10 Jun Zheng , Fuwei Zhao , Youjiang Xu , Xin Dong , Xiaodan Liang

Motion transfer enables controllable video generation by transferring temporal dynamics from a reference video to synthesize a new video conditioned on a target caption. However, existing Diffusion Transformer (DiT)-based methods are…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Samuel Teodoro , Yun Chen , Agus Gunawan , Soo Ye Kim , Jihyong Oh , Munchurl Kim

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Shengrong Gu , Ye Wang , Song Wu , Rui Ma , Qian Wang , Lanjun Wang , Zili Yi

Despite the recent progress of audio-driven video generation, existing methods mostly focus on driving facial movements, leading to non-coherent head and body dynamics. Moving forward, it is desirable yet challenging to generate holistic…

The rising demand for creating lifelike avatars in the digital realm has led to an increased need for generating high-quality human videos guided by textual descriptions and poses. We propose Dancing Avatar, designed to fabricate human…

计算机视觉与模式识别 · 计算机科学 2023-08-16 Bosheng Qin , Wentao Ye , Qifan Yu , Siliang Tang , Yueting Zhuang

Diffusion Transformer has shown remarkable abilities in generating high-fidelity videos, delivering visually coherent frames and rich details over extended durations. However, existing video generation models still fall short in…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Zhaoyang Li , Dongjun Qian , Kai Su , Qishuai Diao , Xiangyang Xia , Chang Liu , Wenfei Yang , Tianzhu Zhang , Zehuan Yuan

Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Jie Liu , Zheng Hui

Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Shuzhou Yang , Xiaoyu Li , Xiaodong Cun , Guangzhi Wang , Lingen Li , Ying Shan , Jian Zhang

In this paper, we present DreaMoving, a diffusion-based controllable video generation framework to produce high-quality customized human videos. Specifically, given target identity and posture sequences, DreaMoving can generate a video of…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Mengyang Feng , Jinlin Liu , Kai Yu , Yuan Yao , Zheng Hui , Xiefan Guo , Xianhui Lin , Haolan Xue , Chen Shi , Xiaowen Li , Aojie Li , Xiaoyang Kang , Biwen Lei , Miaomiao Cui , Peiran Ren , Xuansong Xie

The rapid growth of e-commerce has intensified the demand for Virtual Try-On (VTO) technologies, enabling customers to realistically visualize products overlaid on their own images. Despite recent advances, existing VTO models face…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Qi Li , Shuwen Qiu , Julien Han , Xingzi Xu , Mehmet Saygin Seyfioglu , Kee Kiat Koo , Karim Bouyarmane

While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for portrait generation,…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Junyi Wang , Yudong Guo , Boyang Guo , Shengming Yang , Juyong Zhang

Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Yingcheng Hu , Haowen Gong , Chuanguang Yang , Zhulin An , Yongjun Xu , Songhua Liu

Due to the significant advances in large-scale text-to-image generation by diffusion model (DM), controllable human image generation has been attracting much attention recently. Existing works, such as Controlnet [36], T2I-adapter [20] and…

计算机视觉与模式识别 · 计算机科学 2024-05-17 Binghui Chen , Chongyang Zhong , Wangmeng Xiang , Yifeng Geng , Xuansong Xie

We present MagicMirror, a framework for generating identity-preserved videos with cinematic-level quality and dynamic motion. While recent advances in video diffusion models have shown impressive capabilities in text-to-video generation,…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Yuechen Zhang , Yaoyang Liu , Bin Xia , Bohao Peng , Zexin Yan , Eric Lo , Jiaya Jia
‹ 上一页 1 2 3 10 下一页 ›