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

MCML Authors

Mert Kiray

→ Group Benjamin Busam
 Photogrammetry and Remote Sensing

Nassir Navab

Prof. Dr.

Principal Investigator

Computer Aided Medical Procedures & Augmented Reality

Benjamin Busam

Prof. Dr.

Principal Investigator

Photogrammetry and Remote Sensing

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.

misc RKK+25

---

Preprint

Dec. 2025

---

Authors

A. Rota • M. Kiray • M. A. Karaoglu • P. Ruhkamp • E. De Momi • N. Navab • B. Busam

---

Links

arXiv GitHub

---

Research Areas

 B1 | Computer Vision

 C1 | Medicine