Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE

2022-12-06 · Wen Jiang, Kostas Daniilidis

We propose a novel method for 3D shape completion from a partial observation of a point cloud. Existing methods either operate on a global latent code, which limits the expressiveness of their model, or autoregressively estimate the local features, which is highly computationally extensive. Instead, our method estimates the entire local feature field by a single feedforward network by formulating this problem as a tensor completion problem on the feature volume of the object. Due to the redundancy of local feature volumes, this tensor completion problem can be further reduced to estimating the canonical factors of the feature volume. A hierarchical variational autoencoder (VAE) with tiny MLPs is used to probabilistically estimate the canonical factors of the complete feature volume. The effectiveness of the proposed method is validated by comparing it with the state-of-the-art method quantitatively and qualitatively. Further ablation studies also show the need to adopt a hierarchical architecture to capture the multimodal distribution of possible shapes.

📄 PDF Abstract BibTeX arXiv:2212.03370

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation

2020-04-20 · Oladapo Afolabi, Allen Y. Yang, S. Shankar Sastry

Recent advances in computer graphics and computer vision have found successful application of deep neural network models for 3D shapes based on signed distance functions (SDFs) that are useful for shape representation, r…

3D Shape Classification 3D Shape Retrieval Model Compression Retrieval

Weakly-supervised 3D Shape Completion in the Wild

2020-08-20 · ECCV 2020 8 · Jiayuan Gu, Wei-Chiu Ma, Sivabalan Manivasagam, Wenyuan Zeng 외

3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned. Different from previous methods, we address the problem o…

Point Cloud Registration Pose Estimation

SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping

2023-01-17 · Bipasha Sen, Aditya Agarwal, Gaurav Singh, Brojeshwar B. 외

Recovering full 3D shapes from partial observations is a challenging task that has been extensively addressed in the computer vision community. Many deep learning methods tackle this problem by training 3D shape generati…

3D Shape Generation Pose Estimation valid

AnchorFormer: Point Cloud Completion From Discriminative Nodes

2023-01-01 · CVPR 2023 1 · Zhikai Chen, Fuchen Long, Zhaofan Qiu, Ting Yao 외

Point cloud completion aims to recover the completed 3D shape of an object from its partial observation. A common strategy is to encode the observed points to a global feature vector and then predict the complete poi…

MORPH Object Point Cloud Completion

Learning Generalizable Shape Completion with SIM(3) Equivariance

2025-09-30 · Yuqing Wang, Zhaiyu Chen, Xiao Xiang Zhu arxiv

3D shape completion methods typically assume scans are pre-aligned to a canonical frame. This leaks pose and scale cues that networks may exploit to memorize absolute positions rather than inferring intrinsic geometry. W…