English
Related papers

Related papers: Relax Forcing: Relaxed KV-Memory for Consistent Lo…

200 papers

Real-time talking avatar generation requires low latency and minute-level temporal stability. Autoregressive (AR) forcing enables streaming inference but suffers from exposure bias, which causes errors to accumulate and become irreversible…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Liyuan Cui , Wentao Hu , Wenyuan Zhang , Zesong Yang , Fan Shi , Xiaoqiang Liu

Human motion generation aims to produce plausible human motion sequences according to various conditional inputs, such as text or audio. Despite the feasibility of existing methods in generating motion based on short prompts and simple…

Multimedia · Computer Science 2024-11-12 Bo Han , Hao Peng , Minjing Dong , Yi Ren , Yixuan Shen , Chang Xu

We introduce a method to generate temporally coherent human animation from a single image, a video, or a random noise. This problem has been formulated as modeling of an auto-regressive generation, i.e., to regress past frames to decode…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Tserendorj Adiya , Jae Shin Yoon , Jungeun Lee , Sanghun Kim , Hwasup Lim

A unified autoregressive model is a Transformer-based framework that addresses diverse multimodal tasks (e.g., text, image, video) as a single sequence modeling problem under a shared token space. Such models rely on the KV-cache mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Kunyang Li , Mubarak Shah , Yuzhang Shang

Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Takashi Isobe , Xu Jia , Xin Tao , Changlin Li , Ruihuang Li , Yongjie Shi , Jing Mu , Huchuan Lu , Yu-Wing Tai

Video restoration (VR) aims to recover high-quality videos from degraded ones. Although recent zero-shot VR methods using pre-trained diffusion models (DMs) show good promise, they suffer from approximation errors during reverse diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Hengkang Wang , Yang Liu , Huidong Liu , Chien-Chih Wang , Yanhui Guo , Hongdong Li , Bryan Wang , Ju Sun

Autoregressive (AR) visual generators model images as sequences of discrete tokens and are trained with a next-token likelihood objective. This strict causal supervision optimizes each step based only on the immediate next token, which can…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Yonghao Yu , Lang Huang , Zerun Wang , Runyi Li , Toshihiko Yamasaki

Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended horizons, requiring procedural ordering, persistent action execution, and scene consistency…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Yu Yang , Yue Liao , Jianbiao Mei , Baisen Wang , Xuemeng Yang , Licheng Wen , Jiangning Zhang , Xiangtai Li , Liang Lv , Hanlin Chen , Botian Shi , Yong Liu , Shuicheng Yan , Gim Hee Lee

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Hanchao Liu , Fang-Lue Zhang , Shining Zhang , Tai-Jiang Mu , Shi-Min Hu

Modern video codecs and learning-based approaches struggle for semantic reconstruction at extremely low bit-rates due to reliance on low-level spatiotemporal redundancies. Generative models, especially diffusion models, offer a new paradigm…

Image and Video Processing · Electrical Eng. & Systems 2026-02-06 Maojun Zhang , Haotian Wu , Richeng Jin , Deniz Gunduz , Krystian Mikolajczyk

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Qing Yu , Akihisa Watanabe , Kent Fujiwara

Audio-driven portrait animation, which synthesizes realistic videos from reference images using audio signals, faces significant challenges in real-time generation of high-fidelity, temporally coherent animations. While recent…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Dechao Meng , Steven Xiao , Xindi Zhang , Guangyuan Wang , Peng Zhang , Qi Wang , Bang Zhang , Liefeng Bo

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…

Machine Learning · Computer Science 2021-02-04 Mirza Ramicic , Andrea Bonarini

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Takehiro Aoshima , Yusuke Shinohara , Byeongseon Park

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Wenqi Ouyang , Zeqi Xiao , Danni Yang , Yifan Zhou , Shuai Yang , Lei Yang , Jianlou Si , Xingang Pan

Video generation aims to produce temporally coherent sequences of visual frames, representing a pivotal advancement in Artificial Intelligence Generated Content (AIGC). Compared to static image generation, video generation poses unique…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Zhiyu Yin , Kehai Chen , Xuefeng Bai , Ruili Jiang , Juntao Li , Hongdong Li , Jin Liu , Yang Xiang , Jun Yu , Min Zhang

Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Naoya Fushishita , Antonio Tejero-de-Pablos , Yusuke Mukuta , Tatsuya Harada

Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Tinghui Zhu , Sheng Zhang , James Y. Huang , Selena Song , Xiaofei Wen , Yuankai Li , Hoifung Poon , Muhao Chen

Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer from poor visual and temporal grounding: a model may fabricate object existence, assign…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Yihao Quan , Zeru Shi , Jinman Zhao , Ruixiang Tang

Generating multi-view images from human instructions is crucial for 3D content creation. The primary challenges involve maintaining consistency across multiple views and effectively synthesizing shapes and textures under diverse conditions.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 JiaKui Hu , Yuxiao Yang , Jialun Liu , Jinbo Wu , Chen Zhao , Yanye Lu