Neural fields in visual computing and beyond
Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …
computing problems using methods that employ coordinate‐based neural networks. These …
Neural kernel surface reconstruction
We present a novel method for reconstructing a 3D implicit surface from a large-scale,
sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural …
sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural …
How to represent part-whole hierarchies in a neural network
G Hinton - Neural Computation, 2023 - direct.mit.edu
This article does not describe a working system. Instead, it presents a single idea about
representation that allows advances made by several different groups to be combined into …
representation that allows advances made by several different groups to be combined into …
Growsp: Unsupervised semantic segmentation of 3d point clouds
We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing
methods which primarily rely on a large amount of human annotations for training neural …
methods which primarily rely on a large amount of human annotations for training neural …
Object-Centric Learning with Capsule Networks: A Survey
Capsule networks emerged as a promising alternative to convolutional neural networks for
learning object-centric representations. The idea is to explicitly model part-whole hierarchies …
learning object-centric representations. The idea is to explicitly model part-whole hierarchies …
Sqn: Weakly-supervised semantic segmentation of large-scale 3d point clouds
Labelling point clouds fully is highly time-consuming and costly. As larger point cloud
datasets with billions of points become more common, we ask whether the full annotation is …
datasets with billions of points become more common, we ask whether the full annotation is …
RoReg: Pairwise point cloud registration with oriented descriptors and local rotations
We present RoReg, a novel point cloud registration framework that fully exploits oriented
descriptors and estimated local rotations in the whole registration pipeline. Previous …
descriptors and estimated local rotations in the whole registration pipeline. Previous …
You only hypothesize once: Point cloud registration with rotation-equivariant descriptors
In this paper, we propose a novel local descriptor-based framework, called You Only
Hypothesize Once (YOHO), for the registration of two unaligned point clouds. In contrast to …
Hypothesize Once (YOHO), for the registration of two unaligned point clouds. In contrast to …
Pointersect: Neural rendering with cloud-ray intersection
We propose a novel method that renders point clouds as if they are surfaces. The proposed
method is differentiable and requires no scene-specific optimization. This unique capability …
method is differentiable and requires no scene-specific optimization. This unique capability …
Neural fields as learnable kernels for 3d reconstruction
Abstract We present Neural Kernel Fields: a novel method for reconstructing implicit 3D
shapes based on a learned kernel ridge regression. Our technique achieves state-of-the-art …
shapes based on a learned kernel ridge regression. Our technique achieves state-of-the-art …