English
Related papers

Related papers: OperatorNet: Recovering 3D Shapes From Difference …

200 papers

Shape reconstruction from imaging volumes is a recurring need in medical image analysis. Common workflows start with a segmentation step, followed by careful post-processing and,finally, ad hoc meshing algorithms. As this sequence can be…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Antonio Pepe , Richard Schussnig , Jianning Li , Christina Gsaxner , Dieter Schmalstieg , Jan Egger

Nowadays, service robots are appearing more and more in our daily life. For this type of robot, open-ended object category learning and recognition is necessary since no matter how extensive the training data used for batch learning, the…

Robotics · Computer Science 2021-01-01 Hamidreza Kasaei

In this paper, we introduce a novel method called FRI-Net for 2D floorplan reconstruction from 3D point cloud. Existing methods typically rely on corner regression or box regression, which lack consideration for the global shapes of rooms.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Honghao Xu , Juzhan Xu , Zeyu Huang , Pengfei Xu , Hui Huang , Ruizhen Hu

We propose a novel model for 3D semantic completion from a single depth image, based on a single encoder and three separate generators used to reconstruct different geometric and semantic representations of the original and completed scene,…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Yida Wang , David Joseph Tan , Nassir Navab , Federico Tombari

Reconstructing 3D shape from a single 2D image is a challenging task, which needs to estimate the detailed 3D structures based on the semantic attributes from 2D image. So far, most of the previous methods still struggle to extract semantic…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Xin Wen , Junsheng Zhou , Yu-Shen Liu , Zhen Dong , Zhizhong Han

3D shape analysis has been largely focused on traditional 3D representations of point clouds and meshes, but the discrete nature of these data makes the analysis susceptible to variations in input resolutions. Recent development of neural…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Huan Lei , Hongdong Li , Andreas Geiger , Anthony Dick

Deep neural operators, such as DeepONets, have changed the paradigm in high-dimensional nonlinear regression from function regression to (differential) operator regression, paving the way for significant changes in computational engineering…

We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model shape correspondence as a labelling problem, where each point of a query shape receives a label…

Computer Vision and Pattern Recognition · Computer Science 2017-08-01 Or Litany , Tal Remez , Emanuele Rodolà , Alex M. Bronstein , Michael M. Bronstein

Inferring the 3D shape of an object from an RGB image has shown impressive results, however, existing methods rely primarily on recognizing the most similar 3D model from the training set to solve the problem. These methods suffer from poor…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Haozhe Xie , Hongxun Yao , Shangchen Zhou , Shengping Zhang , Xiaoshuai Sun , Wenxiu Sun

Operator learning offers a robust framework for approximating mappings between infinite-dimensional function spaces. It has also become a powerful tool for solving inverse problems in the computational sciences. This chapter surveys…

Numerical Analysis · Mathematics 2025-12-08 Nicholas H. Nelsen , Yunan Yang

Most of the computer vision architectures nowadays are built upon the well-known foundation operations: fully-connected layers, convolutions and multi-head self-attention blocks. In this paper we propose a novel foundation operation -…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Vladimir Korviakov , Denis Koposov

The convolution operator is the fundamental building block of modern convolutional neural networks (CNNs), owing to its simplicity, translational equivariance, and efficient implementation. However, its structure as a fixed, linear,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Simone Cammarasana

Operator learning trains a neural network to map functions to functions. An ideal operator learning framework should be mesh-free in the sense that the training does not require a particular choice of discretization for the input functions,…

Numerical Analysis · Mathematics 2022-12-15 Zecheng Zhang , Wing Tat Leung , Hayden Schaeffer

Many physical processes in science and engineering are naturally represented by operators between infinite-dimensional function spaces. The problem of operator learning, in this context, seeks to extract these physical processes from…

Machine Learning · Computer Science 2024-01-22 Hao Liu , Biraj Dahal , Rongjie Lai , Wenjing Liao

We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images. Reconstructing general articulating object categories % has important applications, but is challenging since…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Ge Zhang , Or Litany , Srinath Sridhar , Leonidas Guibas

We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures that rely on vector representations. We consider matrices as…

Machine Learning · Computer Science 2018-02-06 Kien Do , Truyen Tran , Svetha Venkatesh

We present HOReeNet, which tackles the novel task of manipulating images involving hands, objects, and their interactions. Especially, we are interested in transferring objects of source images to target images and manipulating 3D hand…

Computer Vision and Pattern Recognition · Computer Science 2022-11-14 Changhwa Lee , Junuk Cha , Hansol Lee , Seongyeong Lee , Donguk Kim , Seungryul Baek

One challenge that remains open in 3D deep learning is how to efficiently represent 3D data to feed deep networks. Recent works have relied on volumetric or point cloud representations, but such approaches suffer from a number of issues…

Computer Vision and Pattern Recognition · Computer Science 2019-01-25 Jhony K. Pontes , Chen Kong , Sridha Sridharan , Simon Lucey , Anders Eriksson , Clinton Fookes

Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this work, we propose a data driven non-iterative algorithm to overcome the shortcomings of earlier…

Computer Vision and Pattern Recognition · Computer Science 2017-08-18 Suhas Lohit , Kuldeep Kulkarni , Ronan Kerviche , Pavan Turaga , Amit Ashok

Existing 3D surface representation approaches are unable to accurately classify pixels and their orientation lying on the boundary of an object. Thus resulting in coarse representations which usually require post-processing steps to extract…

Computer Vision and Pattern Recognition · Computer Science 2019-01-23 Mateusz Michalkiewicz , Jhony K. Pontes , Dominic Jack , Mahsa Baktashmotlagh , Anders Eriksson