Spatially-Varying Outdoor Lighting Estimation from Intrinsics

TL;DR

SOLID-Net is a neural network that estimates spatially-varying outdoor lighting from a single image by combining global sky maps with local geometric information, outperforming previous methods.

Contribution

The paper introduces SOLID-Net and the SOLID-Img dataset for spatially-varying outdoor lighting estimation from a single image.

Findings

SOLID-Net outperforms previous methods on synthetic and real datasets.

The new dataset provides ground truth for local lighting and intrinsic cues.

Spatially-varying local lighting maps improve outdoor scene understanding.

Abstract

We present SOLID-Net, a neural network for spatially-varying outdoor lighting estimation from a single outdoor image for any 2D pixel location. Previous work has used a unified sky environment map to represent outdoor lighting. Instead, we generate spatially-varying local lighting environment maps by combining global sky environment map with warped image information according to geometric information estimated from intrinsics. As no outdoor dataset with image and local lighting ground truth is readily available, we introduce the SOLID-Img dataset with physically-based rendered images and their corresponding intrinsic and lighting information. We train a deep neural network to regress intrinsic cues with physically-based constraints and use them to conduct global and local lightings estimation. Experiments on both synthetic and real datasets show that SOLID-Net significantly outperforms previous methods.