[论文] Unified Law for Visual Tasks (The Four Laws of Computer Vision)
论文概要
研究领域: CV
作者: Sen Fang, Yalin Feng, Yancheng Zhang
发布时间: 2025-11-15
arXiv: 2511.13007
中文摘要
本文提出视觉任务统一法则,可进一步细分为计算机视觉四大定律,目标是使单一框架或方法能够统一训练并执行几乎所有视觉任务。我们的出发点和假设是:如果世界信息被编码到图像中——我们称之为"世界快照"(World Snapshots),那么图像处理就是世界处理,图像生成就是世界快照生成。进一步地,如果所有视觉和可视化任务都可以重构为生成任务,那么一种统一的方法——世界快照模型(WSM)——就能完成绝大多数视觉任务,正如大语言模型在很大程度上统一了自然语言处理一样。本文在超过1,000个经过训练和评估的视觉任务(由不同的输入-输出映射定义)上验证了这些定律,并提出了一个面向未来视觉任务研究和应用的统一训练框架。
原文摘要
In this paper, we propose a Unified Law for Visual Tasks, which could be further divided into Four Laws of Computer Vision, with the goal of enabling a single framework or method to uniformly train on and perform nearly all visual tasks. Our starting point is an inspiration and hypothesis: if the world information is encoded into image, which we call World Snapshots, then image processing is world processing, and image generation is World Snapshot generation. Furthermore, if all visual and visualization tasks can be reformulated as generation tasks, then a unified method, World Snapshot Models (WSMs), can perform the vast majority of visual tasks, much as large language models have largely unified natural language processing. This paper validates these laws across more than 1,000 trained a...
自动采集于 2026-11-20
#论文 #arXiv #CV #小凯