GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints
This work addresses depth estimation challenges in indoor scenes, which is incremental as it builds on existing self-supervised methods to improve specific issues.
The paper tackled inconsistent depth estimation in textureless areas and at object boundaries in indoor self-supervised depth estimation by proposing GAM-Depth, which uses a gradient-aware mask and semantic constraints, achieving state-of-the-art performance on datasets like NYUv2, ScanNet, and InteriorNet.
Self-supervised depth estimation has evolved into an image reconstruction task that minimizes a photometric loss. While recent methods have made strides in indoor depth estimation, they often produce inconsistent depth estimation in textureless areas and unsatisfactory depth discrepancies at object boundaries. To address these issues, in this work, we propose GAM-Depth, developed upon two novel components: gradient-aware mask and semantic constraints. The gradient-aware mask enables adaptive and robust supervision for both key areas and textureless regions by allocating weights based on gradient magnitudes.The incorporation of semantic constraints for indoor self-supervised depth estimation improves depth discrepancies at object boundaries, leveraging a co-optimization network and proxy semantic labels derived from a pretrained segmentation model. Experimental studies on three indoor datasets, including NYUv2, ScanNet, and InteriorNet, show that GAM-Depth outperforms existing methods and achieves state-of-the-art performance, signifying a meaningful step forward in indoor depth estimation. Our code will be available at https://github.com/AnqiCheng1234/GAM-Depth.