OmniSR: Shadow Removal under Direct and Indirect Lighting

TL;DR

OmniSR introduces a new synthetic dataset and a novel neural network architecture that effectively removes shadows caused by both direct and indirect lighting in indoor and outdoor scenes.

Contribution

The paper presents a comprehensive synthetic dataset and an innovative shadow removal network that explicitly incorporates semantic and geometric priors for improved performance.

Findings

Outperforms existing shadow removal methods

Effectively generalizes to diverse indoor and outdoor scenes

Handles shadows from both direct and indirect illumination

Abstract

Shadows can originate from occlusions in both direct and indirect illumination. Although most current shadow removal research focuses on shadows caused by direct illumination, shadows from indirect illumination are often just as pervasive, particularly in indoor scenes. A significant challenge in removing shadows from indirect illumination is obtaining shadow-free images to train the shadow removal network. To overcome this challenge, we propose a novel rendering pipeline for generating shadowed and shadow-free images under direct and indirect illumination, and create a comprehensive synthetic dataset that contains over 30,000 image pairs, covering various object types and lighting conditions. We also propose an innovative shadow removal network that explicitly integrates semantic and geometric priors through concatenation and attention mechanisms. The experiments show that our method outperforms state-of-the-art shadow removal techniques and can effectively generalize to indoor and outdoor scenes under various lighting conditions, enhancing the overall effectiveness and applicability of shadow removal methods.