S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation
Xiaotian Chen, Yuwang Wang, Xuejin Chen, Wenjun Zeng
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/microsoft/S2R-DepthNetOfficialIn paperpytorch★ 167
- github.com/MindSpore-paper-code-3/code8/tree/main/DepthNetmindspore★ 0
- github.com/code-implementation1/Code1/tree/main/DepthNetmindspore★ 0
- github.com/2023-MindSpore-4/Code3/tree/main/DepthNetmindspore★ 0
Abstract
Human can infer the 3D geometry of a scene from a sketch instead of a realistic image, which indicates that the spatial structure plays a fundamental role in understanding the depth of scenes. We are the first to explore the learning of a depth-specific structural representation, which captures the essential feature for depth estimation and ignores irrelevant style information. Our S2R-DepthNet (Synthetic to Real DepthNet) can be well generalized to unseen real-world data directly even though it is only trained on synthetic data. S2R-DepthNet consists of: a) a Structure Extraction (STE) module which extracts a domaininvariant structural representation from an image by disentangling the image into domain-invariant structure and domain-specific style components, b) a Depth-specific Attention (DSA) module, which learns task-specific knowledge to suppress depth-irrelevant structures for better depth estimation and generalization, and c) a depth prediction module (DP) to predict depth from the depth-specific representation. Without access of any real-world images, our method even outperforms the state-of-the-art unsupervised domain adaptation methods which use real-world images of the target domain for training. In addition, when using a small amount of labeled real-world data, we achieve the state-ofthe-art performance under the semi-supervised setting. The code and trained models are available at https://github.com/microsoft/S2R-DepthNet.