Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding

• URL: http://arxiv.org/abs/2103.07838v1
• Date: Sun, 14 Mar 2021 03:52:53 GMT
• Title: Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding
• Authors: Xin Wen and Zhizhong Han and Yan-Pei Cao and Pengfei Wan and Wen Zheng and Yu-Shen Liu
• Abstract summary: 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.
• Score: 57.23678891670394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we present a novel unpaired point cloud completion network, named Cycle4Completion, to infer the complete geometries from a partial 3D object. Previous unpaired completion methods merely focus on the learning of geometric correspondence from incomplete shapes to complete shapes, and ignore the learning in the reverse direction, which makes them suffer from low completion accuracy due to the limited 3D shape understanding ability. To address this problem, we propose two simultaneous cycle transformations between the latent spaces of complete shapes and incomplete ones. The insight of cycle transformation is to promote networks to understand 3D shapes by learning to generate complete or incomplete shapes from their complementary ones. Specifically, the first cycle transforms shapes from incomplete domain to complete domain, and then projects them back to the incomplete domain. This process learns the geometric characteristic of complete shapes, and maintains the shape consistency between the complete prediction and the incomplete input. Similarly, the inverse cycle transformation starts from complete domain to incomplete domain, and goes back to complete domain to learn the characteristic of incomplete shapes. We provide a comprehensive evaluation in experiments, which shows that our model with the learned bidirectional geometry correspondence outperforms state-of-the-art unpaired completion methods.

Related papers

• Self-supervised Shape Completion via Involution and Implicit Correspondences [89.18705005095359]
  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.
  arXiv  Detail & Related papers  (2024-09-24T10:04:38Z)
• Geometrically Consistent Partial Shape Matching [50.29468769172704]
  Finding correspondences between 3D shapes is a crucial problem in computer vision and graphics. An often neglected but essential property of matching geometrics is consistency. We propose a novel integer linear programming partial shape matching formulation.
  arXiv  Detail & Related papers  (2023-09-10T12:21:42Z)
• Implicit Shape Completion via Adversarial Shape Priors [46.48590354256945]
  We present a novel neural implicit shape method for partial point cloud completion. We combine a conditional Deep-SDF architecture with learned, adversarial shape priors. We train a PointNet++ discriminator that impels the generator to produce plausible, globally consistent reconstructions.
  arXiv  Detail & Related papers  (2022-04-21T12:49:59Z)
• MFM-Net: Unpaired Shape Completion Network with Multi-stage Feature Matching [38.63975659511946]
  We propose a novel unpaired shape completion network, named MFM-Net, which decomposes the learning of geometric correspondence into multi-stages. MFM-Net makes use of a more comprehensive understanding to establish the geometric correspondence between complete and incomplete shapes.
  arXiv  Detail & Related papers  (2021-11-23T16:10:06Z)
• 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)
• PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths [54.459879603473034]
  We design a novel neural network, named PMP-Net, to mimic the behavior of an earth mover. It moves each point of the incomplete input to complete the point cloud, where the total distance of point moving paths should be shortest. It learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target.
  arXiv  Detail & Related papers  (2020-12-07T01:34:38Z)
• Weakly-supervised 3D Shape Completion in the Wild [91.04095516680438]
  We address the problem of learning 3D complete shape from unaligned and real-world partial point clouds. We propose a weakly-supervised method to estimate both 3D canonical shape and 6-DoF pose for alignment, given multiple partial observations. Experiments on both synthetic and real data show that it is feasible and promising to learn 3D shape completion through large-scale data without shape and pose supervision.
  arXiv  Detail & Related papers  (2020-08-20T17:53:42Z)

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.