English
Related papers

Related papers: Fully Convolutional Mesh Autoencoder using Efficie…

200 papers

Neural networks transform high-dimensional data into compact, structured representations, often modeled as elements of a lower dimensional latent space. In this paper, we present an alternative interpretation of neural models as dynamical…

Machine Learning · Computer Science 2026-03-26 Marco Fumero , Luca Moschella , Emanuele Rodolà , Francesco Locatello

We present 14 autoencoders, 15 kernels and 14 multilayer perceptrons for electron micrograph restoration and compression. These have been trained for transmission electron microscopy (TEM), scanning transmission electron microscopy (STEM)…

Computer Vision and Pattern Recognition · Computer Science 2018-08-30 Jeffrey M. Ede

We present a new approach for representing and reconstructing multidimensional magnetic resonance imaging (MRI) data. Our method builds on a novel, learned feature-based image representation that disentangles different types of features,…

Image and Video Processing · Electrical Eng. & Systems 2026-01-01 Ruiyang Zhao , Fan Lam

The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the…

Machine Learning · Computer Science 2017-08-29 Prasoon Goyal , Zhiting Hu , Xiaodan Liang , Chenyu Wang , Eric Xing

Spatial transformations are enablers in a variety of medical image analysis applications that entail aligning images to a common coordinate systems. Population analysis of such transformations is expected to capture the underlying image and…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Riddhish Bhalodia , Shireen Y. Elhabian , Ladislav Kavan , Ross T. Whitaker

There is an increasing interest in applying deep learning to 3D mesh segmentation. We observe that 1) existing feature-based techniques are often slow or sensitive to feature resizing, 2) there are minimal comparative studies and 3)…

Graphics · Computer Science 2018-02-09 David George , Xianghua Xie , Gary KL Tam

Deep generative models have become increasingly effective at producing realistic images from randomly sampled seeds, but using such models for controllable manipulation of existing images remains challenging. We propose the Swapping…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Taesung Park , Jun-Yan Zhu , Oliver Wang , Jingwan Lu , Eli Shechtman , Alexei A. Efros , Richard Zhang

Image convolution with complex kernels is a fundamental operation in photography, scientific imaging, and animation effects, yet direct dense convolution is computationally prohibitive on resource-limited devices. Existing approximations,…

Graphics · Computer Science 2026-05-20 Zhizhen Wu , Zhe Cao , Yuchi Huo

Transformer-based Self-supervised Representation Learning methods learn generic features from unlabeled datasets for providing useful network initialization parameters for downstream tasks. Recently, self-supervised learning based upon…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Jincen Jiang , Xuequan Lu , Lizhi Zhao , Richard Dazeley , Meili Wang

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects…

Graphics · Computer Science 2020-12-07 Jie Yang , Lin Gao , Qingyang Tan , Yihua Huang , Shihong Xia , Yu-Kun Lai

Mesh-agnostic models have advantages in terms of processing unstructured spatial data and incorporating partial differential equations. Recently, they have been widely studied for constructing physics-informed neural networks, but they need…

Fluid Dynamics · Physics 2024-04-22 Runze Li , Yufei Zhang , Haixin Chen

The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares…

Image and Video Processing · Electrical Eng. & Systems 2022-02-08 Tianyu Ma , Alan Q. Wang , Adrian V. Dalca , Mert R. Sabuncu

3D morphable models are widely used for the shape representation of an object class in computer vision and graphics applications. In this work, we focus on deep 3D morphable models that directly apply deep learning on 3D mesh data with a…

Computer Vision and Pattern Recognition · Computer Science 2021-05-06 Zhixiang Chen , Tae-Kyun Kim

3D Morphable Models (3DMMs) are statistical models that represent facial texture and shape variations using a set of linear bases and more particular Principal Component Analysis (PCA). 3DMMs were used as statistical priors for…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Yuxiang Zhou , Jiankang Deng , Irene Kotsia , Stefanos Zafeiriou

Unsupervised pre-training was a critical technique for training deep neural networks years ago. With sufficient labeled data and modern training techniques, it is possible to train very deep neural networks from scratch in a purely…

Computer Vision and Pattern Recognition · Computer Science 2017-03-29 Jianfeng Dong , Xiao-Jiao Mao , Chunhua Shen , Yu-Bin Yang

Deep learning has significantly advanced medical imaging analysis, yet variations in image resolution remain an overlooked challenge. Most methods address this by resampling images, leading to either information loss or computational…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Ashay Patel , Michela Antonelli , Sebastien Ourselin , M. Jorge Cardoso

This paper presents the first classical Convolutional Neural Network (CNN) that can be applied directly to data from unstructured finite element meshes or control volume grids. CNNs have been hugely influential in the areas of image…

Numerical Analysis · Mathematics 2025-02-13 Claire E. Heaney , Yuling Li , Omar K. Matar , Christopher C. Pain

Unregistered surface meshes, especially raw 3D scans, present significant challenges for automatic computation of plausible deformations due to the lack of established point-wise correspondences and the presence of noise in the data. In…

Graphics · Computer Science 2025-09-01 Thomas Besnier , Sylvain Arguillère , Mohamed Daoudi

We propose a new 'Bi-Reduced Space' approach to solving 3D Variational Data Assimilation using Convolutional Autoencoders. We prove that our approach has the same solution as previous methods but has significantly lower computational…

Machine Learning · Computer Science 2021-01-07 Julian Mack , Rossella Arcucci , Miguel Molina-Solana , Yi-Ke Guo

We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 Evangelos Ntavelis , Aliaksandr Siarohin , Kyle Olszewski , Chaoyang Wang , Luc Van Gool , Sergey Tulyakov