视觉自回归模型综述
A Survey on Vision Autoregressive Model
AI总结：
本文系统性回顾了视觉自回归模型，构建了涵盖图像与视频生成、医学图像分析等多任务的分类体系，全面评估现有方法并提出了未来研究的挑战与方向。
摘要：
自回归模型在自然语言处理（NLP）中展现出了卓越的性能，具有出色的可扩展性、适应性和泛化能力。受其在NLP领域显著成功的启发，近期针对计算机视觉的自回归模型得到了深入研究，其通过将视觉数据表示为视觉标记来执行下一标记预测，从而实现了对广泛视觉任务的自回归建模，涵盖视觉生成、视觉理解，以及近期出现的利用单一自回归模型统一视觉生成与理解的多模态生成。本文对视觉自回归模型进行了系统性回顾，包括构建现有方法的分类体系，并重点阐述了它们的主要贡献、优势和局限性，覆盖图像生成、视频生成、图像编辑、动作生成、医学图像分析、3D生成、机器人操作、统一多模态生成等多种视觉任务。此外，我们调查并分析了自回归模型的最新进展，包括在各种评估数据集上对现有方法的全面基准测试与讨论。最后，我们概述了未来研究的关键挑战与有前景的方向，为进一步推动视觉自回归模型的发展提供了路线图。
英文摘要：
Autoregressive models have demonstrated great performance in natural language processing (NLP) with impressive scalability, adaptability and generalizability. Inspired by their notable success in NLP field, autoregressive models have been intensively investigated recently for computer vision, which perform next-token predictions by representing visual data as visual tokens and enables autoregressive modelling for a wide range of vision tasks, ranging from visual generation and visual understanding to the very recent multimodal generation that unifies visual generation and understanding with a single autoregressive model. This paper provides a systematic review of vision autoregressive models, including the development of a taxonomy of existing methods and highlighting their major contributions, strengths, and limitations, covering various vision tasks such as image generation, video generation, image editing, motion generation, medical image analysis, 3D generation, robotic manipulation, unified multimodal generation, etc. Besides, we investigate and analyze the latest advancements in autoregressive models, including thorough benchmarking and discussion of existing methods across various evaluation datasets. Finally, we outline key challenges and promising directions for future research, offering a roadmap to guide further advancements in vision autoregressive models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
