Related papers: Statistical properties of 3D cell geometry from 2D…
Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined graph through a series of graph convolutions, leading to…
The gene expression profile of a tissue averages the expression profiles of all cells in this tissue. Digital tissue deconvolution (DTD) addresses the following inverse problem: Given the expression profile $y$ of a tissue, what is the…
Because of the 3D nature of galaxies, an algorithm for constructing spatial density distribution models of galaxies on the basis of galaxy images has many advantages over surface density distribution approximations. We present a method for…
Conventional 2-D scanning electron microscopy (SEM) is commonly used to rapidly and qualitatively evaluate membrane pore structure. Quantitative 2-D analyses of pore sizes can be extracted from SEM, but without information about 3-D spatial…
Our work aims to reconstruct hand-held objects given a single RGB image. In contrast to prior works that typically assume known 3D templates and reduce the problem to 3D pose estimation, our work reconstructs generic hand-held object…
This paper presents a novel framework to recover detailed human body shapes from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, and viewpoints. Prior methods typically attempt to…
Reasoning 3D shapes from 2D images is an essential yet challenging task, especially when only single-view images are at our disposal. While an object can have a complicated shape, individual parts are usually close to geometric primitives…
In this paper, we tackle the problem of 3D human shape estimation from single RGB images. While the recent progress in convolutional neural networks has allowed impressive results for 3D human pose estimation, estimating the full 3D shape…
Modern spatial microscopy has provided developmental biology with powerful research tools. However, the recent significant technological breakthroughs have inevitably led to technical "bottlenecks" for the application of the new procedures…
3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing…
Reshaping accurate and realistic 3D human bodies from anthropometric parameters (e.g., height, chest size, etc.) poses a fundamental challenge for person identification, online shopping and virtual reality. Existing approaches for creating…
3D reconstruction from 2D images is a central problem in computer vision. Recent works have been focusing on reconstruction directly from a single image. It is well known however that only one image cannot provide enough information for…
Rigidity transitions in simple models of confluent cells have been a powerful organizing principle in understanding the dynamics and mechanics of dense biological tissue. In this work we explore the interplay between geometry and rigidity…
It is widely recognized that the shape of epithelial cells is determined by the tension generated by the actomyosin cortex and the adhesion of cells to the substrate and to each other. To account for these biological and structural…
While analyzing mobile systems we often approximate the actual coverage surface and assume an ideal cell shape. In a multi-cellular network, because of its tessellating nature, a hexagon is more preferred than a circular geometry. Despite…
Cell shape is determined by a balance of intrinsic properties of the cell as well as its mechanochemical environment. Inhomogeneous shape changes underly many morphogenetic events and involve spatial gradients in active cellular forces…
Graph neural networks are emerging as promising methods for modeling molecular graphs, in which nodes and edges correspond to atoms and chemical bonds, respectively. Recent studies show that when 3D molecular geometries, such as bond…
Analysis of microscopy images can provide insight into many biological processes. One particularly challenging problem is cell nuclear segmentation in highly anisotropic and noisy 3D image data. Manually localizing and segmenting each and…
Generative models for 2D images has recently seen tremendous progress in quality, resolution and speed as a result of the efficiency of 2D convolutional architectures. However it is difficult to extend this progress into the 3D domain since…
Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…