[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-lenserase-erase-anything-foundation-model":3,"topics-all":35,"news-related-162c36d7-37de-4906-b0dd-cd5ec6f9f455":54},{"id":4,"title":5,"summary":6,"content":7,"original_url":8,"source_id":9,"tags":10,"translations":21,"news_slug":28,"published_at":29,"created_at":30,"modified_at":31,"is_published":32,"publish_type":33,"image_url":14,"view_count":34},"162c36d7-37de-4906-b0dd-cd5ec6f9f455","微软擦除基础模型LensErase:一图一掩码,万物皆可擦","微软联合上海交大等高校发布掩码式擦除基础模型LensErase:一图一掩码,无需文字提示即可抹掉对象、文字、水印及其阴影反射。模型基于文生图底座Lens,通过Mask-Aware RoPE注入掩码信息,在1.01亿组配对数据上预训练,再经SFT与契约引导强化学习精调;六个公开基准与自建500案例评测中均取得大幅提升。","图像编辑里最不起眼却最难做干净的一步,是「擦除」。生成模型越来越擅长往画面里加东西,但要把一个物体连同它的影子、反光一起抹掉,再把露出来的背景补得天衣无缝,同时一丝一毫不动周围的内容——业界一直缺一个统一方案。10 月 13 日,微软联合上海交大、南开大学、中科大、悉尼大学、北京大学等机构的研究团队在 arXiv 发布 LensErase,给出了「擦除基础模型」这个答案([arXiv:2610.18072](https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.18072))。\n\n## 一张图加一个掩码,不用写提示词\n\nLensErase 把交互压到最简:输入图像和选区掩码,不需要任何文字描述。它覆盖的场景包括普通物体、图内文字、水印、多层海报,支持一次处理多个目标与半透明内容,并连同阴影、反射等「关联视觉效果」一起清除——这正是传统修复工具最容易露馅的地方。\n\n## 1.01 亿配对数据打底,强化学习收尾\n\n要让模型「什么都擦得掉」,团队先造了数据:LensErase-100M 包含 1.01 亿组「源图-掩码-目标图」配对样本,横跨物体、水印、大掩码、视觉文字与海报场景。底座选了自家的文生图模型 Lens,把它的生成先验迁移到掩码擦除任务上;为了让掩码信息进入网络,团队提出 Mask-Aware RoPE——一种 3D 旋转位置编码,直接把掩码注入源图 token,不必额外引入一串掩码 token。之后先做监督微调,再用「契约引导、区域感知奖励」的强化学习精调;推理阶段还有 TraceFusion,利用图像残差识别有效编辑区域,区域外内容原样保留。\n\n## 六个公开基准加自建 500 案例验证\n\n评测做了双重设计:六个公开基准加自建的 LensErase-Bench(500 个案例,无需配对真值),既看基于参考图的客观指标,也用视觉语言模型做无参考评估;基准拆出 Removal、Inpainting、Preservation、Cleanliness 四个维度,外加总分与 HiFi Removal。论文称在两组评测中均取得大幅提升,项目页还给出了与 GPT-Image 2.5、Flux2-Erase 的直观对比。代码仓库已开放([GitHub](https:\u002F\u002Fgithub.com\u002FLensFamily\u002FLensErase)),MIT 许可,当前标注「Code coming soon」,模型权重尚未上架,Hugging Face 上引用该论文的模型数仍为 0。\n\n## 所以呢\n\n当「生成」被基础模型标准化之后,「擦除」正在成为下一个被标准化的编辑原语。值得玩味的是,LensErase 把水印也列为正式支持对象:一边是 OpenAI、Anthropic 忙着给 AI 生成内容嵌水印,一边是擦除模型顺手把水印清除做成了基础能力。这场猫鼠游戏的技术天平往哪边倾斜,值得持续盯着。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.18072","7437aeb9-930c-4866-a2e9-48003c1a792b",[11,15,18],{"id":12,"name":13,"slug":13,"description":14,"color":14},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",null,{"id":16,"name":17,"slug":17,"description":14,"color":14},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",{"id":19,"name":20,"slug":20,"description":14,"color":14},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image",[22],{"id":23,"lang":24,"title":25,"summary":26,"content":27},"d7436c05-cabf-4733-8112-5fb2b9a0a1ad","en","LensErase: Microsoft's Erase-Anything Foundation Model","Microsoft-led LensErase removes any object, text or watermark from one image plus one mask, pretrained on 101M pairs for large gains on benchmarks.","The most thankless step in image editing is erasure. Generative models keep getting better at adding things to a picture, but removing an object together with its shadow and reflection, filling the revealed background seamlessly, and leaving the surrounding content untouched pixel-for-pixel has long lacked a unified solution. On October 13, a Microsoft-led team with researchers from Shanghai Jiao Tong University, Nankai University, USTC, the University of Sydney and Peking University released LensErase on arXiv, framing erasure as a foundation-model task ([arXiv:2610.18072](https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.18072)).\n\n## One image, one mask, no prompt\n\nLensErase compresses the interaction to the minimum: an input image and a selection mask, with no text description required. Covered scenarios include general objects, visual text, watermarks and layered posters, multiple targets and semi-transparent content in a single pass, plus associated visual effects such as shadows and reflections — exactly where traditional retouching tools tend to fail.\n\n## 101 million paired examples, then reinforcement learning\n\nTo make a model that can erase anything, the team first built the data: LensErase-100M contains 101.07 million source-mask-target triplets spanning objects, watermarks, large masks, visual text and posters. The base is their own text-to-image model Lens, whose generative prior is adapted to mask-based erasing. To feed mask information into the network, the authors propose Mask-Aware RoPE, a 3D rotary positional encoding that injects the mask directly into source-image tokens without a separate mask token sequence. The model then goes through supervised fine-tuning and reinforcement learning with contract-guided, region-aware rewards; at inference, TraceFusion uses image residuals to identify the effective edit region and keeps everything outside it untouched.\n\n## Six public benchmarks plus a 500-case internal bench\n\nEvaluation is doubled up: six public benchmarks plus the proposed LensErase-Bench (500 cases, no paired ground-truth required), scored both by reference-based objective metrics and reference-free VLM evaluation. The bench breaks out Removal, Inpainting, Preservation and Cleanliness, plus an Overall Score and HiFi Removal. The paper reports substantial improvements across both evaluation families, and the project page adds qualitative comparisons against GPT-Image 2.5 and Flux2-Erase. The code repository is up ([GitHub](https:\u002F\u002Fgithub.com\u002FLensFamily\u002FLensErase)) under an MIT license, currently marked \"Code coming soon\" — no model weights are hosted yet, and the count of Hugging Face models citing the paper is still zero.\n\n## So what\n\nOnce generation has been standardized by foundation models, erasure is becoming the next standardized editing primitive. Notably, LensErase lists watermarks as a first-class supported target: while OpenAI and Anthropic race to embed provenance watermarks into AI-generated content, an erase-anything model quietly makes watermark removal a baseline capability. Which way this cat-and-mouse game tips is worth watching closely.","lenserase-erase-anything-foundation-model","2026-10-15T21:08:38Z","2026-10-15T21:08:54.529996Z","2026-10-15T21:08:54.530007Z",true,"agent",137,[36,45],{"slug":37,"tag_slug":37,"title_zh":38,"title_en":39,"intro_zh":40,"intro_en":41,"id":42,"is_active":32,"created_at":43,"modified_at":44},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":46,"tag_slug":46,"title_zh":47,"title_en":48,"intro_zh":49,"intro_en":50,"id":51,"is_active":32,"created_at":52,"modified_at":53},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":55},[56,61,66,71,76,81],{"id":57,"title":58,"news_slug":59,"published_at":60},"bbbda7ff-b1c7-4142-b37f-2b3fd0547e02","Fibo 2.0 开源:生成编辑合一,登顶开源编辑榜","bria-fibo-2-0-unified-editing-generation","2026-10-21T21:08:11+00:00",{"id":62,"title":63,"news_slug":64,"published_at":65},"3bf416bb-a989-4b02-8341-dbafc7c96c48","MOSS-Image 开源:5B 双语生图,文字排版可编程","moss-image-bilingual-text-rendering-base","2026-10-18T19:08:44+00:00",{"id":67,"title":68,"news_slug":69,"published_at":70},"a7095e70-a6c5-46b6-a616-446825bce5cf","Editable Visual Design：腾讯混元论文让 AI 设计稿带真实图层，直接拖拽改版","tencent-editable-visual-design-agent","2026-09-06T13:08:40+00:00",{"id":72,"title":73,"news_slug":74,"published_at":75},"7cc1b87c-fe06-495a-9c01-9516d0c16354","腾讯混元 HunyuanImage-3.0 全面开源：80B 总参 \u002F 13B 激活的自回归 MoE，把多模态理解和生图拉到同一框架","tencent-hunyuanimage-3-moe-autoregressive","2026-08-05T01:00:00+00:00",{"id":77,"title":78,"news_slug":79,"published_at":80},"f1397080-206a-469f-846c-932a4b3ab8f9","京东开源 JoyAI-Image：统一多模态基础模型，把「理解-生成-编辑」拧成一个闭环","jd-joyai-image","2026-07-20T06:00:00+00:00",{"id":82,"title":83,"news_slug":84,"published_at":85},"ab4cf67e-175a-470b-9512-9d767be79fc6","Boogu-Image-0.1 开源家族：用比对手少一个数量级的数据，把\"理解+生成\"统一做到闭源水平","boogu-image-0-1-10b-unified-turbo","2026-06-26T14:00:00+00:00"]