Abstract
AbstractIn general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.
Funder
H2020 European Research Council
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Software
Cited by
14 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Realistic Fusion of Virtual Materials and Hands for AR through Intrinsic Decomposition;2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct);2023-10-16
2. Intrinsic Appearance Decomposition Using Point Cloud Representation;2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW);2023-10-02
3. PanoStyle: Semantic, Geometry-Aware and Shading Independent Photorealistic Style Transfer for Indoor Panoramic Scenes;2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW);2023-10-02
4. IDTransformer: Transformer for Intrinsic Image Decomposition;2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW);2023-10-02
5. DPF: Learning Dense Prediction Fields with Weak Supervision;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06