中文
相关论文

相关论文: Goodbye Drift: Anchored Tree Sampling for Long-Hor…

200 篇论文

Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Chonghyuk Song , Michal Stary , Boyuan Chen , George Kopanas , Vincent Sitzmann

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

Auto-regressive video generation enables long video synthesis by iteratively conditioning each new batch of frames on previously generated content. However, recent work has shown that such pipelines suffer from severe temporal drift, where…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Ariel Shaulov , Eitan Shaar , Amit Edenzon , Lior Wolf

Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free approaches fall into two categories: extensions of bidirectional models, which are tightly…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Jangho Park , Geon Yeong Park , Gihyun Kwon , Jong Chul Ye

Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending…

计算机视觉与模式识别 · 计算机科学 2025-10-03 Justin Cui , Jie Wu , Ming Li , Tao Yang , Xiaojie Li , Rui Wang , Andrew Bai , Yuanhao Ban , Cho-Jui Hsieh

Closed-loop driving simulation requires real-time interaction beyond short offline clips, pushing current driving world models toward autoregressive (AR) rollout. Existing AR distillation approaches typically rely on frame sinks or…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Conglang Zhang , Yifan Zhan , Qingjie Wang , Zhanpeng Ouyang , Yu Li , Zihao Yang , Xiaoyang Guo , Weiqiang Ren , Qian Zhang , Zhen Dong , Yinqiang Zheng , Wei Yin , Zhengqing Chen

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Chong Cheng , Xianda Chen , Tao Xie , Wei Yin , Weiqiang Ren , Qian Zhang , Xiaoyang Guo , Hao Wang

We propose Drift-Resistant Navigation World Model, a generative model that mitigates both perceptual drift and geometric drift in conventional rollout-based navigation world models. Existing methods recursively feed generated content into…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Po-Chien Luan , Zimin Xia , Wuyang Li , Yang Gao , Alexandre Alahi

Recent diffusion-based video generators have achieved remarkable visual fidelity and prompt controllability, yet scaling them to ultra-high-resolution (UHR) long videos remains prohibitively expensive. The difficulty is especially…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Ziyang Mai , Yuyao Zhang , Yu-Wing Tai

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

Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition generation on globally reconstructed 3D scenes by rendering…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Zun Wang , Han Lin , Jaehong Yoon , Jaemin Cho , Yue Zhang , Mohit Bansal

It is hard to densely track a nonrigid object in long term, which is a fundamental research issue in the computer vision community. This task often relies on estimating pairwise correspondences between images over time where the error is…

计算机视觉与模式识别 · 计算机科学 2016-03-08 Wenbin Li , Darren Cosker , Matthew Brown

Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from context limitations, visual drift due to positional…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Jintao Chen , Chengyu Bai , Junjun Hu , Xinda Xue , Mu Xu

Long-context video modeling is essential for enabling generative models to function as world simulators, as they must maintain temporal coherence over extended time spans. However, most existing models are trained on short clips, limiting…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Yuchao Gu , Weijia Mao , Mike Zheng Shou

Recently, autoregressive (AR) video diffusion models have achieved remarkable performance. However, due to their limited training durations, a train-test gap emerges when testing at longer horizons, leading to rapid visual degradations.…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Haodong Li , Shaoteng Liu , Zhe Lin , Manmohan Chandraker

Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Xunzhi Xiang , Zixuan Duan , Guiyu Zhang , Haiyu Zhang , Zhe Gao , Junta Wu , Shaofeng Zhang , Tengfei Wang , Qi Fan , Chunchao Guo

While recent advancements in text-to-video diffusion models enable high-quality short video generation from a single prompt, generating real-world long videos in a single pass remains challenging due to limited data and high computational…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Subin Kim , Seoung Wug Oh , Jui-Hsien Wang , Joon-Young Lee , Jinwoo Shin

State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In this paper, we argue that many errors,…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Mariam Hassan , Bastien Van Delft , Wuyang Li , Alexandre Alahi

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

Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Yuyang You , Yongzhi Li , Jiahui Li , Yadong Mu , Quan Chen , Peng Jiang
‹ 上一页 1 2 3 10 下一页 ›