Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition
원문 초록
Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep convolutional neural network (CNN). Although deep learning (DL) has been recently used to handle this application, the current DL methods train the network only on synthetic images as obtaining ground truth reflectance and shading for real images is difficult. Therefore, these methods fail to produce reasonable results on real images and often perform worse than the non-DL techniques. We overcome this limitation by proposing a novel hybrid approach to train our network on both synthetic and real images. Specifically, in addition to directly supervising the network using synthetic images, we train the network by enforcing it to produce the same reflectance for a pair of images of the same real-world scene with different illuminations. Furthermore, we improve the results by incorporating a bilateral solver layer into our system during both training and test stages. Experimental results show that our approach produces better results than the state-of-the-art DL and non-DL methods on various synthetic and real datasets both visually and numerically.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training
MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields
Colorful Diffuse Intrinsic Image Decomposition in the Wild
A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering
Exploiting Diffusion Prior for Generalizable Dense Prediction
HyperDID: Hyperspectral Intrinsic Image Decomposition with Deep Feature Embedding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.