Related papers: OperatorNet: Recovering 3D Shapes From Difference …
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…
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…
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.…
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,…
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…
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…
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…
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…
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…
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 -…
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,…
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,…
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…
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…
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…
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…
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…
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…
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…