CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering
Authors:
Preprint
Abstract
Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data for training CNN-based intrinsic image decomposition models, then applying these learned models to real-world images. To that end, we present \ICG, a new, large-scale dataset of physically-based rendered images of scenes with full ground truth decompositions. The rendering process we use is carefully designed to yield high-quality, realistic images, which we find to be crucial for this problem domain. We also propose a new end-to-end training method that learns better decompositions by leveraging \ICG, and optionally IIW and SAW, two recent datasets of sparse annotations on real-world images. Surprisingly, we find that a decomposition network trained solely on our synthetic data outperforms the state-of-the-art on both IIW and SAW, and performance improves even further when IIW and SAW data is added during training. Our work demonstrates the suprising effectiveness of carefully-rendered synthetic data for the intrinsic images task.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Intrinsic Decompositions for Image EditingComputer Graphics Forum, 2017
- AnL1image transform for edge-preserving smoothing and scene-level intrinsic decompositionACM Transactions on Graphics, 2015
- Shape, Illumination, and Reflectance from ShadingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Intrinsic images in the wildACM Transactions on Graphics, 2014
- SLIC Superpixels Compared to State-of-the-Art Superpixel MethodsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- A Closed-Form Solution to Retinex with Nonlocal Texture ConstraintsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Photographic tone reproduction for digital imagesACM Transactions on Graphics, 2002
- Lightness and Retinex TheoryJournal of the Optical Society of America, 1971