Jean Ponce

33

Papers

375

Total Citations

Papers (33)

Unsupervised Object Discovery and Localization in the Wild: Part-Based Matching With Bottom-Up Region Proposals

Learning to Compose Hypercolumns for Visual Correspondence

A New Statistical Model of Star Speckles for Learning to Detect and Characterize Exoplanets in Direct Imaging Observations

Robust Image Filtering Using Joint Static and Dynamic Guidance

Consistency of Silhouettes and Their Duals

Proposal Flow

General Models for Rational Cameras and the Case of Two-Slit Projections

Kernel Square-Loss Exemplar Machines for Image Retrieval

Coordinate-Free Carlsson-Weinshall Duality and Relative Multi-View Geometry

SFNet: Learning Object-Aware Semantic Correspondence

Unsupervised Image Matching and Object Discovery as Optimization

Minimal Solutions to Relative Pose Estimation From Two Views Sharing a Common Direction With Unknown Focal Length

An Image Quality Assessment Dataset for Portraits

The Joint Image Handbook

Unsupervised Object Discovery and Tracking in Video Collections

SCNet: Learning Semantic Correspondence

An Efficient Solution to the Homography-Based Relative Pose Problem With a Common Reference Direction

Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features

Lucas-Kanade Reloaded: End-to-End Super-Resolution From Raw Image Bursts

Unsupervised Layered Image Decomposition Into Object Prototypes

WALDO: Future Video Synthesis Using Object Layer Decomposition and Parametric Flow Prediction

End-to-end Interpretable Learning of Non-blind Image Deblurring

Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration

Toward Unsupervised, Multi-Object Discovery in Large-Scale Image Collections

Active Learning Strategies for Weakly-Supervised Object Detection

Weakly-Supervised Alignment of Video With Text

Dense Optical Tracking: Connecting the Dots

Learning a Convolutional Neural Network for Non-Uniform Motion Blur Removal

A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding

CCVS: Context-aware Controllable Video Synthesis

Large-Scale Unsupervised Object Discovery

Online Learning and Control of Complex Dynamical Systems from Sensory Input

VICRegL: Self-Supervised Learning of Local Visual Features