中文
相关论文

相关论文: HiAR: Efficient Autoregressive Long Video Generati…

200 篇论文

Generating high-quality stereo videos requires consistent depth perception and temporal coherence across frames. Despite advances in image and video synthesis using diffusion models, producing high-quality stereo videos remains a…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Jian Shi , Qian Wang , Zhenyu Li , Wenqing Cui , Ramzi Idoughi , Peter Wonka

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Ming Chen , Liyuan Cui , Wenyuan Zhang , Haoxian Zhang , Yan Zhou , Xiaohan Li , Songlin Tang , Jiwen Liu , Borui Liao , Hejia Chen , Xiaoqiang Liu , Pengfei Wan

Image-to-video (I2V) generation tasks always suffer from keeping high fidelity in the open domains. Traditional image animation techniques primarily focus on specific domains such as faces or human poses, making them difficult to generalize…

计算机视觉与模式识别 · 计算机科学 2024-03-06 Weijie Li , Litong Gong , Yiran Zhu , Fanda Fan , Biao Wang , Tiezheng Ge , Bo Zheng

The increasing demand for immersive AR/VR applications and spatial intelligence has heightened the need to generate high-quality scene-level and 360${\deg}$ panoramic video. However, most video diffusion models are constrained by limited…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Jinxiu Liu , Shaoheng Lin , Yinxiao Li , Ming-Hsuan Yang

Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable long-horizon generation: classical diffusion-based approaches…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Yu Shang , Lei Jin , Yiding Ma , Xin Zhang , Chen Gao , Wei Wu , Yong Li

The field of portrait image animation, driven by speech audio input, has experienced significant advancements in the generation of realistic and dynamic portraits. This research delves into the complexities of synchronizing facial movements…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Mingwang Xu , Hui Li , Qingkun Su , Hanlin Shang , Liwei Zhang , Ce Liu , Jingdong Wang , Yao Yao , Siyu Zhu

Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a dual speed bottleneck: the sequential AR stage and the iterative multi-step denoising of…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Zhen Zou , Xiaoxiao Ma , Mingde Yao , Jie Huang , LinJiang Huang , Feng Zhao

Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture long-range dependencies and produce fluent, context-aware…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Junhao Chen , Yulia Tsvetkov , Xiaochuang Han

Autoregressive (AR) language models have emerged as powerful solutions for zero-shot text-to-speech (TTS) synthesis, capable of generating natural speech from a few seconds of audio prompts. However, conventional AR-based TTS systems…

音频与语音处理 · 电气工程与系统科学 2025-08-27 Chun Yat Wu , Jiajun Deng , Guinan Li , Qiuqiang Kong , Simon Lui

Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the global trajectory coherence of diffusion-based policies. However,…

机器人学 · 计算机科学 2026-03-31 Daichi Yashima , Koki Seno , Shuhei Kurita , Yusuke Oda , Komei Sugiura

We study why continuous diffusion language models (DLMs) have lagged behind discrete diffusion approaches despite their appealing continuous generative dynamics. Under a controlled token--recovery study, we identify token rounding, the…

计算与语言 · 计算机科学 2026-03-04 Junzhe Shen , Jieru Zhao , Ziwei He , Zhouhan Lin

Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, they incorporate image context in a linear 1D order by…

计算机视觉与模式识别 · 计算机科学 2021-08-20 Patrick Esser , Robin Rombach , Andreas Blattmann , Björn Ommer

Cameras and LiDAR are essential sensors for autonomous vehicles. Camera-LiDAR data fusion compensate for deficiencies of stand-alone sensors but relies on precise extrinsic calibration. Many learning-based calibration methods predict…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Ni Ou , Zhuo Chen , Xinru Zhang , Junzheng Wang

Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Hancheng Ye , Jiakang Yuan , Renqiu Xia , Xiangchao Yan , Tao Chen , Junchi Yan , Botian Shi , Bo Zhang

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Jiayi Luo , Qiyan Liu , Tengyang Wang , JunHao Liu , Jiayu Chen , Cong Wang , Hanxin Zhu , Chen Gao , Xiaobin Hu , Qingyun Sun , Zhibo Chen

Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consistency across shots and flexibly generating videos of…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Xiangyang Luo , Qingyu Li , Xiaokun Liu , Wenyu Qin , Miao Yang , Meng Wang , Pengfei Wan , Di Zhang , Kun Gai , Shao-Lun Huang

Video diffusion models have revolutionized generative video synthesis, but they are imprecise, slow, and can be opaque during generation -- keeping users in the dark for a prolonged period. In this work, we propose DiffusionBrowser, a…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Susung Hong , Chongjian Ge , Zhifei Zhang , Jui-Hsien Wang

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

机器学习 · 计算机科学 2025-02-10 Justin Deschenaux , Caglar Gulcehre

Video-to-music (V2M) generation aims to create music that aligns with visual content. However, two main challenges persist in existing methods: (1) the lack of explicit rhythm modeling hinders audiovisual temporal alignments; (2)…

声音 · 计算机科学 2025-11-13 Shulei Ji , Zihao Wang , Jiaxing Yu , Xiangyuan Yang , Shuyu Li , Songruoyao Wu , Kejun Zhang

In the current research landscape, multimodal autoregressive (AR) models have shown exceptional capabilities across various domains, including visual understanding and generation. However, complex tasks such as style-aligned text-to-image…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Yi Wu , Lingting Zhu , Shengju Qian , Lei Liu , Wandi Qiao , Lequan Yu , Bin Li