UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision

TL;DR

UnReflectAnything is an RGB-only method that removes highlights from images by predicting highlight maps and reconstructing diffuse images, using synthetic supervision from a novel rendering pipeline, applicable to natural and surgical images.

Contribution

It introduces a Virtual Highlight Synthesis pipeline for training highlight removal models without paired data, leveraging physically plausible rendering techniques.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Generalizes well across natural and surgical imagery.

Operates effectively with only RGB input.

Abstract

Specular highlights distort appearance, obscure texture, and hinder geometric reasoning in both natural and surgical imagery. We present UnReflectAnything, an RGB-only framework that removes highlights from a single image by predicting a highlight map together with a reflection-free diffuse reconstruction. The model uses a frozen vision transformer encoder to extract multi-scale features, a lightweight head to localize specular regions, and a token-level inpainting module that restores corrupted feature patches before producing the final diffuse image. To overcome the lack of paired supervision, we introduce a Virtual Highlight Synthesis pipeline that renders physically plausible specularities using monocular geometry, Fresnel-aware shading, and randomized lighting which enables training on arbitrary RGB images with correct geometric structure. UnReflectAnything generalizes across natural and surgical domains where non-Lambertian surfaces and non-uniform lighting create severe highlights and it achieves competitive performance with state-of-the-art results on several benchmarks. Project Page: https://alberto-rota.github.io/UnReflectAnything/