Results 11 to 20 of about 882 (37)
Compact Model Representation for 3D Reconstruction
, 2017 3D reconstruction from 2D images is a central problem in computer vision. Recent works have been focusing on reconstruction directly from a single image.
Eriksson, Anders +5 more
core +2 more sources
Shape from Shading through Shape Evolution
, 2017 In this paper, we address the shape-from-shading problem by training deep networks with synthetic images. Unlike conventional approaches that combine deep learning and synthetic imagery, we propose an approach that does not need any external shape ...
Deng, Jia, Yang, Dawei
core +1 more source
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
, 2018 We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to handle large scenes
Bokeloh, Martin +5 more
core +1 more source
VConv-DAE: Deep Volumetric Shape Learning Without Object Labels
, 2016 With the advent of affordable depth sensors, 3D capture becomes more and more ubiquitous and already has made its way into commercial products. Yet, capturing the geometry or complete shapes of everyday objects using scanning devices (e.g.
GE Hinton +7 more
core +1 more source
Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis
, 2017 We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input shape, our method first infers a low-resolution -- but complete -- output ...
Dai, Angela +2 more
core +1 more source
Learning Material-Aware Local Descriptors for 3D Shapes
, 2018 Material understanding is critical for design, geometric modeling, and analysis of functional objects. We enable material-aware 3D shape analysis by employing a projective convolutional neural network architecture to learn material- aware descriptors ...
Averkiou, Melinos +7 more
core +1 more source
PyCOOL - a Cosmological Object-Oriented Lattice code written in Python
, 2012 There are a number of different phenomena in the early universe that have to be studied numerically with lattice simulations. This paper presents a graphics processing unit (GPU) accelerated Python program called PyCOOL that solves the evolution of ...
+29 more
core +1 more source
Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
, 2018 We present an Adaptive Octree-based Convolutional Neural Network (Adaptive O-CNN) for efficient 3D shape encoding and decoding. Different from volumetric-based or octree-based CNN methods that represent a 3D shape with voxels in the same resolution, our ...
Liu, Yang +3 more
core +1 more source
Color Dipole Moments for Edge Detection
, 2009 Dipole and higher moments are physical quantities used to describe a charge distribution. In analogy with electromagnetism, it is possible to define the dipole moments for a gray-scale image, according to the single aspect of a gray-tone map.
Sparavigna, Amelia
core
Animating ultra-complex voxel scenes through shell deformation [PDF]
, 2010 version draft du mémoireInternational audienceVoxel representations have many advantages, such as ordered traversal during rendering and trivial very decent LOD through MIPmap. Special effect companies such Digital Domain or Rhythm&Hues now ex- tensively
Crassin, Cyril, Rios Pavia, Daniel
core +1 more source