2019 · 16 citations · 17 references
ComputingArchitectural Representation3D ModelingComputer VisionMachine Vision3D ReconstructionDepth EstimationGenerative ModelingScene ReconstructionScene UnderstandingBenchmark DatasetsGenerative Adversarial NetworksLabelsScene CompletionSemantic Scene ReconstructionSemantic Scene Understanding
We address the task of 3D semantic scene completion, i.e., given a single depth image, we predict the semantic labels and occupancy of voxels in a 3D grid representing the scene. In light of the recently introduced generative adversarial networks (GAN), our goal is to explore the potential of this model and the efficiency of various important design choices. Our results show that using conditional GANs outperforms the vanilla GAN setup. We evaluate these architecture designs on several datasets. Based on our experiments, we demonstrate that GANs are able to outperform the performance of a baseline 3D CNN in case of clean annotations, but they suffer from poorly aligned annotations.
17
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 22.1K citations
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations