中文
相关论文

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

200 篇论文

Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment:…

计算与语言 · 计算机科学 2026-04-08 Dat Nguyen-Cong , Tung Kieu , Hoang Thanh-Tung

Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to…

计算机视觉与模式识别 · 计算机科学 2023-09-26 Zheng Chen , Yulun Zhang , Ding Liu , Bin Xia , Jinjin Gu , Linghe Kong , Xin Yuan

Diffusion models have achieved impressive results in world modeling tasks, including novel view generation from sparse inputs. However, most existing diffusion-based NVS methods generate target views jointly via an iterative denoising…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Wenbin Teng , Gonglin Chen , Haiwei Chen , Yajie Zhao

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive (AR) language models, inspired by their success in natural…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Yizhuo Li , Yuying Ge , Yixiao Ge , Ying Shan , Ping Luo

Conventional wisdom suggests that autoregressive models are used to process discrete data. When applied to continuous modalities such as visual data, Visual AutoRegressive modeling (VAR) typically resorts to quantization-based approaches to…

计算机视觉与模式识别 · 计算机科学 2025-05-13 Chenze Shao , Fandong Meng , Jie Zhou

Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rollout, suffer from…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Junyi Ouyang , Wenbin Teng , Gonglin Chen , Yajie Zhao , Haiwei Chen

Although powerful for image generation, consistent and controllable video is a longstanding problem for diffusion models. Video models require extensive training and computational resources, leading to high costs and large environmental…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Muhammad Haaris Khan , Hadrien Reynaud , Bernhard Kainz

Dataset distillation often prioritizes global semantic proximity when creating small surrogate datasets for original large-scale ones. However, object semantics are inherently hierarchical. For example, the position and appearance of a…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Lin Zhao , Xinru Jiang , Xi Xiao , Qihui Fan , Lei Lu , Yanzhi Wang , Xue Lin , Octavia Camps , Pu Zhao , Jianyang Gu

Autoregressive transformers have recently shown impressive image generation quality and efficiency on par with state-of-the-art diffusion models. Unlike diffusion architectures, autoregressive models can naturally incorporate arbitrary…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Yixiao Chen , Zhiyuan Ma , Guoli Jia , Che Jiang , Jianjun Li , Bowen Zhou

We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion models is vital as, first, there is no sufficiently large HDR…

图形学 · 计算机科学 2025-03-19 Mojtaba Bemana , Thomas Leimkühler , Karol Myszkowski , Hans-Peter Seidel , Tobias Ritschel

Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail…

计算机视觉与模式识别 · 计算机科学 2024-06-07 Enhui Ma , Lijun Zhou , Tao Tang , Zhan Zhang , Dong Han , Junpeng Jiang , Kun Zhan , Peng Jia , Xianpeng Lang , Haiyang Sun , Di Lin , Kaicheng Yu

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Yicheng Ji , Zhizhou Zhong , Jun Zhang , Qin Yang , XiTai Jin , Ying Qin , Wenhan Luo , Shuiyang Mao , Wei Liu , Huan Li

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Tianyi Liu , Ye Lu , Linfeng Zhang , Chen Cai , Jianjun Gao , Yi Wang , Kim-Hui Yap , Lap-Pui Chau

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…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Liyuan Cui , Wentao Hu , Wenyuan Zhang , Zesong Yang , Fan Shi , Xiaoqiang Liu

The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Jiamin Wang , Yichen Yao , Xiang Feng , Hang Wu , Yaming Wang , Qingqiu Huang , Yuexin Ma , Xinge Zhu

Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…

计算机视觉与模式识别 · 计算机科学 2022-06-24 Jonathan Ho , Tim Salimans , Alexey Gritsenko , William Chan , Mohammad Norouzi , David J. Fleet

Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and…

计算机视觉与模式识别 · 计算机科学 2025-02-26 Peipei Yuan , Zijing Xie , Shuo Ye , Hong Chen , Yulong Wang

We present ART$\boldsymbol{\cdot}$V, an efficient framework for auto-regressive video generation with diffusion models. Unlike existing methods that generate entire videos in one-shot, ART$\boldsymbol{\cdot}$V generates a single frame at a…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Wenming Weng , Ruoyu Feng , Yanhui Wang , Qi Dai , Chunyu Wang , Dacheng Yin , Zhiyuan Zhao , Kai Qiu , Jianmin Bao , Yuhui Yuan , Chong Luo , Yueyi Zhang , Zhiwei Xiong

Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance. Their success has been recently expanded to text generation via generating all tokens within a sequence concurrently.…

计算与语言 · 计算机科学 2023-12-14 Tong Wu , Zhihao Fan , Xiao Liu , Yeyun Gong , Yelong Shen , Jian Jiao , Hai-Tao Zheng , Juntao Li , Zhongyu Wei , Jian Guo , Nan Duan , Weizhu Chen

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence,…

计算机视觉与模式识别 · 计算机科学 2025-09-25 Tianwei Yin , Qiang Zhang , Richard Zhang , William T. Freeman , Fredo Durand , Eli Shechtman , Xun Huang