M
Michel Gangnet
Researcher at Microsoft
Publications - 15
Citations - 5061
Michel Gangnet is an academic researcher from Microsoft. The author has contributed to research in topics: Interpolation & Particle filter. The author has an hindex of 13, co-authored 15 publications receiving 4777 citations.
Papers
More filters
Proceedings ArticleDOI
Poisson image editing
TL;DR: Using generic interpolation machinery based on solving Poisson equations, a variety of novel tools are introduced for seamless editing of image regions, which permits the seamless importation of both opaque and transparent source image regions into a destination region.
Book ChapterDOI
Color-Based Probabilistic Tracking
TL;DR: This work introduces a new Monte Carlo tracking technique based on the same principle of color histogram distance, but within a probabilistic framework, and introduces the following ingredients: multi-part color modeling to capture a rough spatial layout ignored by global histograms, incorporation of a background color model when relevant, and extension to multiple objects.
Proceedings ArticleDOI
JetStream: probabilistic contour extraction with particles
TL;DR: A sequential Monte-Carlo technique, termed JetStream, is proposed that enables constraints on curvature, corners, and contour parallelism to be mobilized, all of which are infeasible under exact optimization.
Proceedings ArticleDOI
Sequential Monte Carlo fusion of sound and vision for speaker tracking
TL;DR: Stereo sound and vision can indeed be fused effectively, to make a system more capable than with either modality on its own, using generative probabilistic models and particle filtering.
Book ChapterDOI
Towards Improved Observation Models for Visual Tracking: Selective Adaptation
TL;DR: The approach proposed here is to adapt selectively, allowing adaptation only during periods when two particular conditions are met: that the object should be both present and in motion.