Sciweavers

317 search results - page 32 / 64
» 3-D Depth Reconstruction from a Single Still Image
Sort
View
ICCV
2007
IEEE
16 years 1 months ago
Depth Information by Stage Classification
Recently, methods for estimating 3D scene geometry or absolute scene depth information from 2D image content have been proposed. However, general applicability of these methods in...
André Redert, Arnold W. M. Smeulders, Jan-M...
ICCV
2009
IEEE
16 years 2 months ago
Complete Multi-View Reconstruction of Dynamic Scenes from Probabilistic Fusion of Narrow and Wide Baseline Stereo
This paper presents a novel approach to achieve accurate and complete multi-view reconstruction of dynamic scenes (or 3D videos). 3D videos consist in sequences of 3D models in mot...
Tony Tung, Shohei Nobuhara, Takashi Matsuyama
ISCAS
2008
IEEE
195views Hardware» more  ISCAS 2008»
15 years 6 months ago
Multi-view depth video coding using depth view synthesis
— Depth information indicates the distance of an object in the three dimensional (3D) scene from the camera view-point, typically represented by eight bits. Since the depth map i...
Sang-Tae Na, Kwan-Jung Oh, Cheon Lee, Yo-Sung Ho
SI3D
2006
ACM
15 years 5 months ago
The depth discontinuity occlusion camera
Rendering a scene using a single depth image suffers from disocclusion errors as the view translates away from the reference view. We present the depth discontinuity occlusion cam...
Voicu Popescu, Daniel G. Aliaga
114
Voted
CVPR
2012
IEEE
13 years 2 months ago
Filling large holes in LiDAR data by inpainting depth gradients
We introduce a technique to fill large holes in LiDAR data sets. We combine concepts from patch-based image inpainting and gradient-domain image editing to simultaneously fill b...
David Doria, Richard J. Radke