Sciweavers

ACCV
2010
Springer
13 years 6 months ago
Image-Based 3D Modeling via Cheeger Sets
We propose a novel variational formulation for generating 3D models of objects from a single view. Based on a few user scribbles in an image, the algorithm automatically extracts t...
Eno Töppe, Martin R. Oswald, Daniel Cremers, ...
ACCV
2010
Springer
13 years 6 months ago
Four Color Theorem for Fast Early Vision
Recent work on early vision such as image segmentation, image restoration, stereo matching, and optical flow models these problems using Markov Random Fields. Although this formula...
Radu Timofte, Luc J. Van Gool
ACCV
2010
Springer
13 years 6 months ago
Hemispherical Confocal Imaging Using Turtleback Reflector
Abstract. We propose a new imaging method called hemispherical confocal imaging to clearly visualize a particular depth in a 3-D scene. The key optical component is a turtleback re...
Yasuhiro Mukaigawa, Seiichi Tagawa, Jaewon Kim, Ra...
ACCV
2010
Springer
13 years 6 months ago
An Efficient RANSAC for 3D Object Recognition in Noisy and Occluded Scenes
In this paper, we present an efficient algorithm for 3D object recognition in presence of clutter and occlusions in noisy, sparse and unsegmented range data. The method uses a robu...
Chavdar Papazov, Darius Burschka
ACCV
2010
Springer
13 years 6 months ago
Efficient Visual Object Tracking with Online Nearest Neighbor Classifier
Abstract. A tracking-by-detection framework is proposed that combines nearest-neighbor classification of bags of features, efficient subwindow search, and a novel feature selection...
Steve Gu, Ying Zheng, Carlo Tomasi
ACCV
2010
Springer
13 years 6 months ago
A Weak Structure Model for Regular Pattern Recognition Applied to Facade Images
Abstract. We propose a novel method for recognition of structured images and demonstrate it on detection of windows in facade images. Given an ability to obtain local low-level dat...
Radim Tylecek, Radim Sára
ACCV
2010
Springer
13 years 6 months ago
Multiple Viewpoint Recognition and Localization
This paper presents a novel approach for labeling objects based on multiple spatially-registered images of a scene. We argue that such a multi-view labeling approach is a better fi...
Scott Helmer, David Meger, Marius Muja, James J. L...
ACCV
2010
Springer
13 years 6 months ago
Social Interactive Human Video Synthesis
In this paper, we propose a computational model for social interaction between three people in a conversation, and demonstrate results using human video motion synthesis. We utilis...
Dumebi Okwechime, Eng-Jon Ong, Andrew Gilbert, Ric...
ACCV
2010
Springer
13 years 6 months ago
Finding Human Poses in Videos Using Concurrent Matching and Segmentation
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
Hao Jiang
ACCV
2010
Springer
13 years 6 months ago
A Unified Approach to Segmentation and Categorization of Dynamic Textures
Dynamic textures (DT) are videos of non-rigid dynamical objects, such as fire and waves, which constantly change their shape and appearance over time. Most of the prior work on DT ...
Avinash Ravichandran, Paolo Favaro, René Vi...