Probabilistic Detection and Tracking of Motion Boundaries
International Journal of Computer Vision - Special issue on Genomic Signal Processing
Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model
International Journal of Computer Vision - Special issue on statistical and computational theories of vision: Part II
Is Super-Resolution with Optical Flow Feasible?
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Assorted Pixels: Multi-sampled Imaging with Structural Models
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
A Double-Loop Algorithm to Minimize the Bethe Free Energy
EMMCVPR '01 Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Eyeglasses Removal from Face Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image-Based Rendering Using Image-Based Priors
International Journal of Computer Vision
A Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Variational Maximum A Posteriori by Annealed Mean Field Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Why can't José read?: the problem of learning semantic associations in a robot environment
HLT-NAACL-LWM '04 Proceedings of the HLT-NAACL 2003 workshop on Learning word meaning from non-linguistic data - Volume 6
Sequential mean field variational analysis of structured deformable shapes
Computer Vision and Image Understanding
Assorted pixels: multi-sampled imaging with structural models
ACM SIGGRAPH 2006 Courses
Assorted pixels: multi-sampled imaging with structural models
SIGGRAPH '05 ACM SIGGRAPH 2005 Courses
Hallucinating multiple occluded face images of different resolutions
Pattern Recognition Letters
Hallucinating multiple occluded face images of different resolutions
Pattern Recognition Letters - Special issue on vision for crime detection and prevention
Assorted pixels: multi-sampled imaging with structural models
ACM SIGGRAPH 2007 courses
Low-cost super-resolution algorithms implementation over a HW/SW video compression platform
EURASIP Journal on Applied Signal Processing
Limits of Learning-Based Superresolution Algorithms
International Journal of Computer Vision
Learning iterative image reconstruction
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Sequential mean field variational analysis of structured deformable shapes
Computer Vision and Image Understanding
Steerable pyramid-based face hallucination
Pattern Recognition
Brand identification using Gaussian derivative histograms
ICVS'03 Proceedings of the 3rd international conference on Computer vision systems
PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
Super-resolution image reconstruction based on K-means-Markov network
ICNC'09 Proceedings of the 5th international conference on Natural computation
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Robust web image/video super-resolution
IEEE Transactions on Image Processing
Classification and Semantic Mapping of Urban Environments
International Journal of Robotics Research
Directionally adaptive single frame image super resolution
International Journal of Innovative Computing and Applications
Inpainting with image patches for compression
Journal of Visual Communication and Image Representation
Multi-view object tracking using sequential belief propagation
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Solving multilabel MRFs using incremental α-expansion on the GPUs
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
Enhancing face recognition at a distance using super resolution
Proceedings of the on Multimedia and security
A locally linear regression model for boundary preserving regularization in stereo matching
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Single image super-resolution based on space structure learning
Pattern Recognition Letters
Detecting, segmenting and tracking unknown objects using multi-label MRF inference
Computer Vision and Image Understanding
A Comprehensive Survey to Face Hallucination
International Journal of Computer Vision
| Hi-index | 0.00 |
We show a learning-based method for low-level vision problems{estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images. We model that world with a Markov network, learning the network parameters from the examples. Bayesian belief propagation allows us to efficiently find a local maximum of the posterior probability for the scene, given the image. We call this approach VISTA{Vision by Image/Scene TrAining.We apply VISTA to the "super-resolution" problem (estimating high frequency details from a low-resolution image), showing good results. For the motion estimation problem, we show figure/ground discrimination, solution of the aperture problem, and filling-in arising from application of the same probabilistic machinery.