Self-supervised Shape Completion via Involution and Implicit Correspondences

• URL: http://arxiv.org/abs/2409.15939v1
• Date: Tue, 24 Sep 2024 10:04:38 GMT
• Title: Self-supervised Shape Completion via Involution and Implicit Correspondences
• Authors: Mengya Liu, Ajad Chhatkuli, Janis Postels, Luc Van Gool, Federico Tombari,
• Abstract summary: 3D shape completion is traditionally solved using supervised training or by distribution learning on complete shape examples. Recently self-supervised learning approaches that do not require any complete 3D shape examples have gained more interests. We propose a non-adversarial self-supervised approach for the shape completion task.
• Score: 89.18705005095359
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D shape completion is traditionally solved using supervised training or by distribution learning on complete shape examples. Recently self-supervised learning approaches that do not require any complete 3D shape examples have gained more interests. In this paper, we propose a non-adversarial self-supervised approach for the shape completion task. Our first finding is that completion problems can be formulated as an involutory function trivially, which implies a special constraint on the completion function G, such that G(G(X)) = X. Our second constraint on self-supervised shape completion relies on the fact that shape completion becomes easier to solve with correspondences and similarly, completion can simplify the correspondences problem. We formulate a consistency measure in the canonical space in order to supervise the completion function. We efficiently optimize the completion and correspondence modules using "freeze and alternate" strategy. The overall approach performs well for rigid shapes in a category as well as dynamic non-rigid shapes. We ablate our design choices and compare our solution against state-of-the-art methods, showing remarkable accuracy approaching supervised accuracy in some cases.

Related papers

• DiffComplete: Diffusion-based Generative 3D Shape Completion [114.43353365917015]
  We introduce a new diffusion-based approach for shape completion on 3D range scans. We strike a balance between realism, multi-modality, and high fidelity. DiffComplete sets a new SOTA performance on two large-scale 3D shape completion benchmarks.
  arXiv  Detail & Related papers  (2023-06-28T16:07:36Z)
• 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)
• A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching [69.14632473279651]
  We present a scalable algorithm for globally optimizing over the space of geometrically consistent mappings between 3D shapes. We propose a novel primal coupled with a Lagrange dual problem that is several orders of magnitudes faster than previous solvers.
  arXiv  Detail & Related papers  (2022-04-27T09:47:47Z)
• AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation [29.018733252938926]
  Powerful priors allow us to perform inference with insufficient information. We propose an autoregressive prior for 3D shapes to solve multimodal 3D tasks such as shape completion, reconstruction, and generation.
  arXiv  Detail & Related papers  (2022-03-17T17:59:54Z)
• Unsupervised 3D Shape Completion through GAN Inversion [116.27680045885849]
  We present ShapeInversion, which introduces Generative Adrial Network (GAN) inversion to shape completion for the first time. ShapeInversion uses a GAN pre-trained on complete shapes by searching for a latent code that gives a complete shape that best fits the given partial input. On the ShapeNet benchmark, the proposed ShapeInversion outperforms the SOTA unsupervised method, and is comparable with supervised methods that are learned using paired data.
  arXiv  Detail & Related papers  (2021-04-27T17:53:46Z)
• Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding [57.23678891670394]
  We propose two simultaneous cycle transformations between the latent spaces of complete shapes and incomplete ones. We show that our model with the learned bidirectional geometry correspondence outperforms state-of-the-art unpaired completion methods.
  arXiv  Detail & Related papers  (2021-03-14T03:52:53Z)

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.