AI修图新物种：说擦哪就擦哪，连水印一起消失
现在的AI修图工具，让你圈一块区域说“删掉”，它常常连背景一起糊掉，或者留下明显的修补痕迹。这篇论文做了一个专门干“擦除”的通用模型，能处理的不只是物体，还有文字、水印、甚至物体自带的阴影倒影，一次能删多个，而且不管目标是大楼还是小蚂蚁、图片是横是竖，它都接得住。做法上，它先造了一个1亿张“原图+蒙版+干净结果”的训练集，再从一个成熟的文生图模型出发，把“生成”能力改造成“擦除”能力，最后用强化学习专门奖励“擦得干净、不碰周围”。在六个公开测试集上，它的效果都明显超过现有方法。它不是你明天就能装进手机里的功能，但它是“擦除”这件事第一次有了一个像样的通用底座，以后修图软件里的“消除笔”大概率会换成它。
📄 原文摘要(英文)
We introduce LensErase, a general-purpose mask-based Erase Anything foundation model designed to cover a broad spectrum of real-world erase scenarios. LensErase supports diverse objects, visual text, watermarks, associated visual effects, multiple-object removal, and a wide range of object scales, aspect ratios, and image resolutions. First, to enable such broad coverage, we construct LensErase-100M, a large-scale dataset containing 101.07 million paired source-mask-target examples spanning diverse erase scenarios. Second, we pretrain LensErase from the text-to-image model Lens, adapting its strong generative prior to mask-based erasing. To efficiently incorporate the source image and erase mask, we propose Mask-Aware RoPE, a 3D rotary positional encoding that directly injects mask information into the source-image tokens without introducing a separate mask token sequence. Finally, we refine the model through supervised fine-tuning and reinforcement learning with contract-guided, region-aware rewards, and apply TraceFusion at inference to preserve high-fidelity content outside the effective edit region. Across six public benchmarks and the proposed LensErase-Bench, LensErase achieves substantial improvements under both reference-based objective metrics and reference-free VLM evaluation. We hope LensErase can serve as a foundational model for erase-related applications and systems.