CNN architectures for geometric transformation-invariant feature representation in computer vision: a review
A Mumuni, F Mumuni - SN Computer Science, 2021 - Springer
One of the main challenges in machine vision relates to the problem of obtaining robust
representation of visual features that remain unaffected by geometric transformations. This …
representation of visual features that remain unaffected by geometric transformations. This …
Point2mesh: A self-prior for deformable meshes
In this paper, we introduce Point2Mesh, a technique for reconstructing a surface mesh from
an input point cloud. Instead of explicitly specifying a prior that encodes the expected shape …
an input point cloud. Instead of explicitly specifying a prior that encodes the expected shape …
What's the Situation With Intelligent Mesh Generation: A Survey and Perspectives
Intelligent Mesh Generation (IMG) represents a novel and promising field of research,
utilizing machine learning techniques to generate meshes. Despite its relative infancy, IMG …
utilizing machine learning techniques to generate meshes. Despite its relative infancy, IMG …
3D vision with transformers: A survey
The success of the transformer architecture in natural language processing has recently
triggered attention in the computer vision field. The transformer has been used as a …
triggered attention in the computer vision field. The transformer has been used as a …
Tm-net: Deep generative networks for textured meshes
We introduce TM-NET, a novel deep generative model for synthesizing textured meshes in a
part-aware manner. Once trained, the network can generate novel textured meshes from …
part-aware manner. Once trained, the network can generate novel textured meshes from …
Supervoxel convolution for online 3D semantic segmentation
Online 3D semantic segmentation, which aims to perform real-time 3D scene reconstruction
along with semantic segmentation, is an important but challenging topic. A key challenge is …
along with semantic segmentation, is an important but challenging topic. A key challenge is …
Laplacian2mesh: Laplacian-based mesh understanding
Geometric deep learning has sparked a rising interest in computer graphics to perform
shape understanding tasks, such as shape classification and semantic segmentation. When …
shape understanding tasks, such as shape classification and semantic segmentation. When …
Single image 3d shape retrieval via cross-modal instance and category contrastive learning
In this work, we tackle the problem of single image-based 3D shape retrieval (IBSR), where
we seek to find the most matched shape of a given single 2D image from a shape repository …
we seek to find the most matched shape of a given single 2D image from a shape repository …
Subdivision-based mesh convolution networks
Convolutionalneural networks (CNNs) have made great breakthroughs in two-dimensional
(2D) computer vision. However, their irregular structure makes it hard to harness the …
(2D) computer vision. However, their irregular structure makes it hard to harness the …
Laplacian mesh transformer: Dual attention and topology aware network for 3D mesh classification and segmentation
Deep learning-based approaches for shape understanding and processing tasks have
attracted considerable attention. Despite the great progress that has been made, the existing …
attracted considerable attention. Despite the great progress that has been made, the existing …