arXiv (Cornell University) · 2017 · 10 citations · 36 references
Open access
ComputingComputer ScienceComputer VisionMachine LearningMachine Vision3D Imaging3D ReconstructionDepth EstimationMulti-view GeometryScene ReconstructionScene Understanding3D Scene UnderstandingConsistencyDomain AdaptationDomain Adaptation For Depth EstimationKeypoint DetectionKeypoint TrackingRegularization
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan/image. Our key idea is to utilize the fact that predictions from different views of the same or similar objects should be consistent with each other. Such view consistency provides effective regularization for keypoint prediction on unlabeled instances. In addition, we introduce a geometric alignment term to regularize predictions in the target domain. The resulting loss function can be effectively optimized via alternating minimization. We demonstrate the effectiveness of our approach on real datasets and present experimental results showing that our approach is superior to state-of-the-art general-purpose domain adaptation techniques.
36
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · arXiv (Cornell University) · 2015 · 4.7K citations · Full text
3D ShapeNets: A deep representation for volumetric shapes
Zhirong Wu, Shuran Song, Aditya Khosla et al. · 2015 · 4.7K citations · Full text
MeshLab: an Open-Source Mesh Processing Tool
Paolo Cignoni, Marco Callieri, Massimiliano Corsini et al. · ISTI Open Portal · 2008 · 2K citations · Full text