Given a set of calibrated images of a scene, we present an approach that...
Improvements in Earth observation by satellites allow for imagery of eve...
We present a generative document-specific approach to character analysis...
We introduce MegaPose, a method to estimate the 6D pose of novel objects...
This paper describes new techniques for learning atlas-like representati...
Approaches for single-view reconstruction typically rely on viewpoint
an...
We introduce FocalPose, a neural render-and-compare method for jointly
e...
Neural implicit surfaces have become an important technique for multi-vi...
The goal of this work is to efficiently identify visually similar patter...
In this paper, we revisit the classical representation of 3D point cloud...
Illustrations are an essential transmission instrument. For an historian...
Deep multi-view stereo (deep MVS) methods have been developed and extens...
We present an unsupervised learning framework for decomposing images int...
We introduce RoboPose, a method to estimate the joint angles and the 6D
...
We present docExtractor, a generic approach for extracting visual elemen...
We tackle the problem of finding accurate and robust keypoint correspond...
We introduce an approach for recovering the 6D pose of multiple known ob...
The quality and generality of deep image features is crucially determine...
Batch Normalization (BN) is a prominent deep learning technique. In spit...
Recent advances in image clustering typically focus on learning better d...
This paper considers the generic problem of dense alignment between two
...
Historical watermark recognition is a highly practical, yet unsolved
cha...
We propose to represent shapes as the deformation and combination of
lea...
We propose a self-supervised approach to deep surface deformation. Given...
Most deep pose estimation methods need to be trained for specific object...
In this paper, we address the problem of visually guided rearrangement
p...
Localizing an object accurately with respect to a robot is a key step fo...
Deep image generation is becoming a tool to enhance artists and designer...
We present a new deep learning approach for matching deformable shapes b...
We introduce a method for learning to generate the surface of 3D shapes....
Sketch-based modeling strives to bring the ease and immediacy of drawing...
Sketch-based modeling strives to bring the ease and immediacy of drawing...
Convolutional Neural Networks (CNNs) were recently shown to provide
stat...
Discriminative deep learning approaches have shown impressive results fo...
This paper presents an end-to-end convolutional neural network (CNN) for...
We introduce an approach for analyzing the variation of features generat...
In this paper we study the application of convolutional neural networks ...