CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Intrinsic Image Decomposition | IIW (test) | WHDR16.2 | 9 | |
| Intrinsic Decomposition | IIW 5 (test) | WHDR17.5 | 6 | |
| Intrinsic Image Decomposition | ARAP Real-World | CSM R5.431 | 4 | |
| Intrinsic Image Decomposition | ARAP | MSE (R)0.066 | 4 | |
| Intrinsic Image Decomposition | ARAP Synthetic | CSM R1.79 | 4 |