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).

One image, one mask, no prompt

LensErase 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.

101 million paired examples, then reinforcement learning

To 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.

Six public benchmarks plus a 500-case internal bench

Evaluation 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) 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.

So what

Once 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.