Saved in:
Bibliographic Details
Main Authors: Rota, Alberto, Kiray, Mert, Karaoglu, Mert Asim, Ruhkamp, Patrick, De Momi, Elena, Navab, Nassir, Busam, Benjamin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.09583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918244178198528
author Rota, Alberto
Kiray, Mert
Karaoglu, Mert Asim
Ruhkamp, Patrick
De Momi, Elena
Navab, Nassir
Busam, Benjamin
author_facet Rota, Alberto
Kiray, Mert
Karaoglu, Mert Asim
Ruhkamp, Patrick
De Momi, Elena
Navab, Nassir
Busam, Benjamin
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2512_09583
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision
Rota, Alberto
Kiray, Mert
Karaoglu, Mert Asim
Ruhkamp, Patrick
De Momi, Elena
Navab, Nassir
Busam, Benjamin
Computer Vision and Pattern Recognition
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/
title UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.09583