Curriculum DeepSDF

• URL: http://arxiv.org/abs/2003.08593v3
• Date: Thu, 16 Jul 2020 21:18:48 GMT
• Title: Curriculum DeepSDF
• Authors: Yueqi Duan, Haidong Zhu, He Wang, Li Yi, Ram Nevatia, Leonidas J. Guibas
• Abstract summary: We design a "shape curriculum" for learning continuous Signed Distance Function (SDF) on shapes, namely Curriculum DeepSDF. Inspired by how humans learn, Curriculum DeepSDF organizes the learning task in ascending order of difficulty according to the following two criteria: surface accuracy and sample difficulty. Experimental results show that a carefully-designed curriculum leads to significantly better shape reconstructions with the same training data, training epochs and network architecture as DeepSDF.
• Score: 85.03886488645873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When learning to sketch, beginners start with simple and flexible shapes, and then gradually strive for more complex and accurate ones in the subsequent training sessions. In this paper, we design a "shape curriculum" for learning continuous Signed Distance Function (SDF) on shapes, namely Curriculum DeepSDF. Inspired by how humans learn, Curriculum DeepSDF organizes the learning task in ascending order of difficulty according to the following two criteria: surface accuracy and sample difficulty. The former considers stringency in supervising with ground truth, while the latter regards the weights of hard training samples near complex geometry and fine structure. More specifically, Curriculum DeepSDF learns to reconstruct coarse shapes at first, and then gradually increases the accuracy and focuses more on complex local details. Experimental results show that a carefully-designed curriculum leads to significantly better shape reconstructions with the same training data, training epochs and network architecture as DeepSDF. We believe that the application of shape curricula can benefit the training process of a wide variety of 3D shape representation learning methods.

Related papers

• Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries [8.732260277121547]
  Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry.
  arXiv  Detail & Related papers  (2024-08-27T14:54:33Z)
• Explorable Mesh Deformation Subspaces from Unstructured Generative Models [53.23510438769862]
  Deep generative models of 3D shapes often feature continuous latent spaces that can be used to explore potential variations. We present a method to explore variations among a given set of landmark shapes by constructing a mapping from an easily-navigable 2D exploration space to a subspace of a pre-trained generative model.
  arXiv  Detail & Related papers  (2023-10-11T18:53:57Z)
• Cut-and-Approximate: 3D Shape Reconstruction from Planar Cross-sections with Deep Reinforcement Learning [0.0]
  We present to the best of our knowledge the first 3D shape reconstruction network to solve this task. Our method is based on applying a Reinforcement Learning algorithm to learn how to effectively parse the shape.
  arXiv  Detail & Related papers  (2022-10-22T17:48:12Z)
• PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation [59.70430570779819]
  We introduce a data-driven shape completion approach that focuses on completing geometric details of missing regions of 3D shapes. Our key insight is to copy and deform patches from the partial input to complete missing regions. We leverage repeating patterns by retrieving patches from the partial input, and learn global structural priors by using a neural network to guide the retrieval and deformation steps.
  arXiv  Detail & Related papers  (2022-07-24T18:59:09Z)
• Cloud Sphere: A 3D Shape Representation via Progressive Deformation [21.216503294296317]
  This paper is dedicated to discovering distinctive information from the shape formation process. A Progressive Deformation-based Auto-Encoder is proposed to learn the stage-aware description. Experimental results show that the proposed PDAE has the ability to reconstruct 3D shapes with high fidelity.
  arXiv  Detail & Related papers  (2021-12-21T12:10:23Z)
• Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction [61.62191904755521]
  3D freehand US reconstruction is promising in addressing the problem by providing broad range and freeform scan. Existing deep learning based methods only focus on the basic cases of skill sequences. We propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences.
  arXiv  Detail & Related papers  (2021-07-31T16:06:50Z)
• Unsupervised Medical Image Alignment with Curriculum Learning [16.72680081620203]
  We explore different curriculum learning methods for training convolutional neural networks on the task of deformable pairwise 3D medical image registration. Our experiments with an underlying state-of-the-art deep learning model show that curriculum learning can lead to superior results compared to conventional training.
  arXiv  Detail & Related papers  (2021-02-20T20:26:01Z)
• Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization [52.17872739634213]
  We propose a novel 3d shape representation for 3d shape reconstruction from a single image. We train a network to generate a training set which will be fed into another learning algorithm to define the shape.
  arXiv  Detail & Related papers  (2020-10-16T09:52:13Z)
• Semi-Siamese Training for Shallow Face Learning [78.7386209619276]
  We introduce a novel training method named Semi-Siamese Training (SST) A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures.
  arXiv  Detail & Related papers  (2020-07-16T15:20:04Z)
• Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence [31.840880075039944]
  We present a novel learning-based approach for computing correspondences between non-rigid 3D shapes. Key to our method is a feature-extraction network that learns directly from raw shape geometry.
  arXiv  Detail & Related papers  (2020-03-31T15:20:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.