English
Related papers

Related papers: Multimodal Shape Completion via Conditional Genera…

200 papers

This work provides an architecture to enable robotic grasp planning via shape completion. Shape completion is accomplished through the use of a 3D convolutional neural network (CNN). The network is trained on our own new open source dataset…

Robotics · Computer Science 2017-03-03 Jacob Varley , Chad DeChant , Adam Richardson , Joaquín Ruales , Peter Allen

Unlike a conventional background inpainting approach that infers a missing area from image patches similar to the background, face completion requires semantic knowledge about the target object for realistic outputs. Current image…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Haofu Liao , Gareth Funka-Lea , Yefeng Zheng , Jiebo Luo , S. Kevin Zhou

Multi-modal medical image segmentation plays an essential role in clinical diagnosis. It remains challenging as the input modalities are often not well-aligned spatially. Existing learning-based methods mainly consider sharing trainable…

Computer Vision and Pattern Recognition · Computer Science 2021-01-06 Jingkun Chen , Wenqi Li , Hongwei Li , Jianguo Zhang

3D shape reconstruction from a single image is a highly ill-posed problem. Modern deep learning based systems try to solve this problem by learning an end-to-end mapping from image to shape via a deep network. In this paper, we aim to solve…

Computer Vision and Pattern Recognition · Computer Science 2019-08-02 Kejie Li , Ravi Garg , Ming Cai , Ian Reid

The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Dongliang Cao , Florian Bernard

Grasping objects with limited or no prior knowledge about them is a highly relevant skill in assistive robotics. Still, in this general setting, it has remained an open problem, especially when it comes to only partial observability and…

Robotics · Computer Science 2026-01-21 Matthias Humt , Dominik Winkelbauer , Ulrich Hillenbrand , Berthold Bäuml

The problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not correspond to natural objects. Recent research in the field…

Computer Vision and Pattern Recognition · Computer Science 2018-09-14 Jiajun Wu , Chengkai Zhang , Xiuming Zhang , Zhoutong Zhang , William T. Freeman , Joshua B. Tenenbaum

3D shapes captured by scanning devices are often incomplete due to occlusion. 3D shape completion methods have been explored to tackle this limitation. However, most of these methods are only trained and tested on a subset of categories,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Lintai Wu , Junhui Hou , Linqi Song , Yong Xu

Data-driven design approaches based on deep-learning have been introduced in nanophotonics to reduce time-consuming iterative simulations which have been a major challenge. Here, we report the first use of conditional deep convolutional…

Optics · Physics 2019-03-21 Sunae So , Junsuk Rho

We propose a data-driven method for recovering miss-ing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement…

Computer Vision and Pattern Recognition · Computer Science 2017-09-26 Xiaoguang Han , Zhen Li , Haibin Huang , Evangelos Kalogerakis , Yizhou Yu

Heterogeneous face recognition between color image and depth image is a much desired capacity for real world applications where shape information is looked upon as merely involved in gallery. In this paper, we propose a cross-modal deep…

Computer Vision and Pattern Recognition · Computer Science 2017-09-15 Wuming Zhang , Zhixin Shu , Dimitris Samaras , Liming Chen

Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing. To…

Machine Learning · Computer Science 2020-11-13 Changqing Zhang , Yajie Cui , Zongbo Han , Joey Tianyi Zhou , Huazhu Fu , Qinghua Hu

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…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Mengya Liu , Ajad Chhatkuli , Janis Postels , Luc Van Gool , Federico Tombari

Many existing learning-based grasping approaches concentrate on a single embodiment, provide limited generalization to higher DoF end-effectors and cannot capture a diverse set of grasp modes. We tackle the problem of grasping using…

Multimodal alignment constructs a joint latent vector space where modalities representing the same concept map to neighboring latent vectors. We formulate this as an inverse problem and show that, under certain conditions, paired data from…

Machine Learning · Computer Science 2025-06-10 Abhi Kamboj , Minh N. Do

Significant progress has been made in training large generative models for natural language and images. Yet, the advancement of 3D generative models is hindered by their substantial resource demands for training, along with inefficient,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Ka-Hei Hui , Aditya Sanghi , Arianna Rampini , Kamal Rahimi Malekshan , Zhengzhe Liu , Hooman Shayani , Chi-Wing Fu

In this paper we explore the recent topic of point cloud completion, guided by an auxiliary image. We show how it is possible to effectively combine the information from the two modalities in a localized latent space, thus avoiding the need…

Computer Vision and Pattern Recognition · Computer Science 2022-09-21 Emanuele Aiello , Diego Valsesia , Enrico Magli

We introduce a novel framework for evaluating multimodal deep learning models with respect to their language understanding and generalization abilities. In this approach, artificial data is automatically generated according to the…

Computation and Language · Computer Science 2017-04-18 Alexander Kuhnle , Ann Copestake

In this paper, we focus on the task of 3D shape completion from partial point clouds using deep implicit functions. Existing methods seek to use voxelized basis functions or the ones from a certain family of functions (e.g., Gaussians),…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Hui Ying , Tianjia Shao , He Wang , Yin Yang , Kun Zhou

Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data. These two learning mechanisms can, however, conflict with each other and representations can…

Machine Learning · Computer Science 2023-01-24 Rogelio A. Mancisidor , Michael Kampffmeyer , Kjersti Aas , Robert Jenssen