arXiv research

This paper improves 3D pose recovery from 2D images using non-convex regularization.

Geometric Capsule Autoencoders group 3D points into parts and objects.

We propose a method to generate multiple diverse and valid human pose hypotheses in 3D all consistent with the 2D detection of joints in a monocular RGB image. We use a novel generative model uniform (unbiased) in the space of anatomically plausible 3D poses. Our model is compositional (produces a pose by combining par…

We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manne…

Generative model creates realistic dance poses from music.

This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized for a downstream task. We demonstrate this framework on 3D pose estimation by pro…

Generative model disentangles 3D shapes into independent factors.

3d-SMRnet speeds up MPI system matrix recovery to 1 minute with high quality.

New framework predicts diverse, contextually plausible 3D human motions.

The paper proposes a method to learn 3D object pose manifolds using GANs and elasticae.

Paper develops a differentiable approach for 3D imaging models using Fourier slice theorem.

Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of $\ell_1$ regularization, in this paper, we investigate the usage of non-convex regularizations in this problem. Our contribution consists of three parts. First, we propose the leaky capped …

Paper predicts TUG score from gait characteristics using machine learning.

Proposes a model to generate 3D-aware images from 2D images.

Paper tackles unsupervised learning of 3D shapes from single images.

StyleNeRF generates high-resolution images with 3D consistency and style control.

Unsupervised mesh disentanglement separates identity and pose.

We consider the problem of learning object arrangements in a 3D scene. The key idea here is to learn how objects relate to human poses based on their affordances, ease of use and reachability. In contrast to modeling object-object relationships, modeling human-object relationships scales linearly in the number of objec…

3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful r…

Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured by CECT, methods for several important tasks such as subtomogram classification a…

This paper explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, we apply a convolutional neural networ…

Tensor neural network improves human pose classification from 3D skeleton data.

This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.

LatticeNet segments 3D point clouds faster and more efficiently.

We introduce SARR for symmetric object pose estimation, improving CNN performance.

Novel GNN predicts drug-target interactions using protein-ligand 3D structures.

Cellular Electron Cryo-Tomography (CECT) is a powerful imaging technique for the 3D visualization of cellular structure and organization at submolecular resolution. It enables analyzing the native structures of macromolecular complexes and their spatial organization inside single cells. However, due to the high degree …

BPI models 2D patterns on multiple planes and 3D scene from a single image.

The paper learns pose variations within shape populations using constrained mixtures of factor analyzers.

A method for camera calibration using heatmap regression for fisheye images.

New method reconstructs 3D shapes from 2D images using Kendall's shape space.

Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding an…

3D capsule network for point clouds handles rotations and translations.

Proves Borel Conjecture for certain 3D spaces.

Paper proposes Roweisposes for 3D action recognition using generalized eigenvalue problem.

This work provides a guaranteed tensor recovery method by combining low-rankness and smoothness priors.

Paper tackles distributed quantile regression with improved efficiency and support recovery.

In neural networks, it is often desirable to work with various representations of the same space. For example, 3D rotations can be represented with quaternions or Euler angles. In this paper, we advance a definition of a continuous representation, which can be helpful for training deep neural networks. We relate this t…

Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional latent scenes, due to challenges in both modeling and inference. Accounting for th…

New algorithm recovers 3D molecule structures from noisy data.

Improved QSM maps from MRI using deep learning.

Trans-Unet predicts brain folding patterns from 3D point-clouds using novel 3D-to-2D transformation.

New framework uses score-based priors to solve ill-conditioned polynomial equations, improving signal recovery from noisy data.

The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and the design of accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition…

Study on 3D foliated dynamical systems with Hilbert reciprocity law.

A method improves Cryo-EM 3D map refinement by regularizing rotation estimation.

Researchers found spiraling conformal geodesics in 3D space.

This paper presents the first theoretical results showing that stable identification of overcomplete $μ$-coherent dictionaries $Φ\in \mathbb{R}^{d\times K}$ is locally possible from training signals with sparsity levels $S$ up to the order $O(μ^{-2})$ and signal to noise ratios up to $O(\sqrt{d})$. In particular the di…