D
David J. Fleet
Researcher at University of Toronto
Publications - 204
Citations - 30932
David J. Fleet is an academic researcher from University of Toronto. The author has contributed to research in topics: Motion estimation & Computer science. The author has an hindex of 68, co-authored 181 publications receiving 24376 citations. Previous affiliations of David J. Fleet include University of Milano-Bicocca & Queen's University.
Papers
More filters
Journal ArticleDOI
Performance of optical flow techniques
TL;DR: These comparisons are primarily empirical, and concentrate on the accuracy, reliability, and density of the velocity measurements; they show that performance can differ significantly among the techniques the authors implemented.
Journal ArticleDOI
cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination
TL;DR: It is shown that stochastic gradient descent (SGD) and branch-and-bound maximum likelihood optimization algorithms permit the major steps in cryo-EM structure determination to be performed in hours or minutes on an inexpensive desktop computer.
Proceedings ArticleDOI
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Chitwan Saharia,V. K. Chan,Saurabh Saxena,Lala Li,Jay Whang,Emily Denton,Seyed Kamyar Seyed Ghasemipour,Burcu Karagol Ayan,Seyedeh Sara Mahdavi,Raphael Gontijo Lopes,Tim Salimans,Jonathan Ho,David J. Fleet,Mahmood Norouzi +13 more
TL;DR: This work presents Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding, and finds that human raters prefer Imagen over other models in side-by-side comparisons, both in terms of sample quality and image-text alignment.
Journal ArticleDOI
TurboPixels: Fast Superpixels Using Geometric Flows
Alex Levinshtein,A. Stere,Kiriakos N. Kutulakos,David J. Fleet,Sven Dickinson,Kaleem Siddiqi +5 more
TL;DR: A geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels, which yields less undersegmentation than algorithms that lack a compactness constraint while offering a significant speedup over N-cuts, which does enforce compactness.
Journal ArticleDOI
Robust online appearance models for visual tracking
TL;DR: A framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects to provide robustness in the face of image outliers, while adapting to natural changes in appearance such as those due to facial expressions or variations in 3D pose.