Training Data Generating Networks: Shape Reconstruction via Bi-level OptimizationDownload PDF

29 Sept 2021, 00:32 (edited 15 Mar 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: shape reconstruction single image, meta learning, few-shot learning, differentiable optimization, bi-level optimization
  • Abstract: We propose a novel 3d shape representation for 3d shape reconstruction from a single image. Rather than predicting a shape directly, we train a network to generate a training set which will be fed into another learning algorithm to define the shape. The nested optimization problem can be modeled by bi-level optimization. Specifically, the algorithms for bi-level optimization are also being used in meta learning approaches for few-shot learning. Our framework establishes a link between 3D shape analysis and few-shot learning. We combine training data generating networks with bi-level optimization algorithms to obtain a complete framework for which all components can be jointly trained. We improve upon recent work on standard benchmarks for 3d shape reconstruction.
9 Replies