• Publications
  • Influence
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
TLDR
A novel unsupervised learning approach to build features suitable for object detection and classification and to facilitate the transfer of features to other tasks, the context-free network (CFN), a siamese-ennead convolutional neural network is introduced. Expand
A closed form solution to robust subspace estimation and clustering
TLDR
This work uses an augmented Lagrangian optimization framework, which requires a combination of the proposed polynomial thresholding operator with the more traditional shrinkage-thresholding operator, to solve the problem of fitting one or more subspace to a collection of data points drawn from the subspaces and corrupted by noise/outliers. Expand
Low rank subspace clustering (LRSC)
TLDR
This work poses the problem of fitting a union of subspaces to a collection of data points drawn from one or more subspaced and corrupted by noise and/or gross errors as a non-convex optimization problem, and solves the problem using an alternating minimization approach. Expand
Total Variation Blind Deconvolution: The Devil Is in the Details
  • Daniel Perrone, P. Favaro
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 23 June 2014
TLDR
An adaptation of this algorithm, based on the algorithm of Chan and Wong, is introduced and it is shown that, in spite of its extreme simplicity, it is very robust and achieves a performance comparable to the state of the art. Expand
Structure from Motion Causally Integrated Over Time
We describe an algorithm for reconstructing three-dimensional structure and motion causally, in real time from monocular sequences of images. We prove that the algorithm is minimal and stable, in theExpand
Learning to Extract a Video Sequence from a Single Motion-Blurred Image
TLDR
This work presents a deep learning scheme that gradually reconstructs a temporal ordering by sequentially extracting pairs of frames and introduces loss functions invariant to the temporal order, which lets a neural network choose during training what frame to output among the possible combinations. Expand
A geometric approach to shape from defocus
  • P. Favaro, Stefano Soatto
  • Mathematics, Computer Science
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 March 2005
TLDR
A novel approach to shape from defocus, i.e., the problem of inferring the three-dimensional geometry of a scene from a collection of defocused images, is introduced and a simple and efficient method that first learns a set of projection operators from blurred images and then uses these operators to estimate the 3D geometry of the scene from novel blurred images is proposed. Expand
Shape from Defocus via Diffusion
TLDR
This work shows how to bypass the inverse problem of reconstructing 3D structure from blurred images corresponds to an "inverse diffusion" that is notoriously ill posed by using the notion of relative blur. Expand
Boosting Self-Supervised Learning via Knowledge Transfer
TLDR
A novel framework for self-supervised learning is presented that overcomes limitations in designing and comparing different tasks, models, and data domains and achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin. Expand
Representation Learning by Learning to Count
TLDR
This paper uses two image transformations in the context of counting: scaling and tiling to train a neural network with a contrastive loss that produces representations that perform on par or exceed the state of the art in transfer learning benchmarks. Expand
...
1
2
3
4
5
...