SCoDA: Domain Adaptive Shape Completion for Real Scans
This addresses the domain gap issue in 3D shape completion for real scans, which is incremental as it adapts existing methods to a new dataset.
The paper tackles the problem of 3D shape completion from real-world scans by proposing a domain adaptation task to bridge the gap between synthetic and real data, achieving an improvement of 6%~7% mIoU in experiments.
3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between synthetic and real data limits the generalizability of these methods. Thus, we propose a new task, SCoDA, for the domain adaptation of real scan shape completion from synthetic data. A new dataset, ScanSalon, is contributed with a bunch of elaborate 3D models created by skillful artists according to scans. To address this new task, we propose a novel cross-domain feature fusion method for knowledge transfer and a novel volume-consistent self-training framework for robust learning from real data. Extensive experiments prove our method is effective to bring an improvement of 6%~7% mIoU.