1 code implementation • ECCV 2020 • Zak Murez, Tarrence van As, James Bartolozzi, Ayan Sinha, Vijay Badrinarayanan, Andrew Rabinovich
Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene.
Ranked #1 on 3D Reconstruction on ScanNet
1 code implementation • ECCV 2020 • Ayan Sinha, Zak Murez, James Bartolozzi, Vijay Badrinarayanan, Andrew Rabinovich
Cost volume based approaches employing 3D convolutional neural networks (CNNs) have considerably improved the accuracy of MVS systems.
Ranked #2 on Depth Estimation on ScanNetV2
no code implementations • 18 Mar 2020 • Zhengyang Wu, Srivignesh Rajendran, Tarrence van As, Joelle Zimmermann, Vijay Badrinarayanan, Andrew Rabinovich
With the emergence of Virtual and Mixed Reality (XR) devices, eye tracking has received significant attention in the computer vision community.
no code implementations • 16 Mar 2020 • Ameya Phalak, Vijay Badrinarayanan, Andrew Rabinovich
We introduce Scan2Plan, a novel approach for accurate estimation of a floorplan from a 3D scan of the structural elements of indoor environments.
16 code implementations • CVPR 2020 • Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.
Ranked #2 on Visual Place Recognition on Berlin Kudamm
no code implementations • 12 Sep 2019 • Prajwal Chidananda, Ayan Sinha, Adithya Rao, Douglas Lee, Andrew Rabinovich
2D Key-point estimation is an important precursor to 3D pose estimation problems for human body and hands.
no code implementations • 24 Aug 2019 • Zhengyang Wu, Srivignesh Rajendran, Tarrence van As, Joelle Zimmermann, Vijay Badrinarayanan, Andrew Rabinovich
Eye gaze estimation and simultaneous semantic understanding of a user through eye images is a crucial component in Virtual and Mixed Reality; enabling energy efficient rendering, multi-focal displays and effective interaction with 3D content.
no code implementations • 25 Apr 2019 • Ameya Phalak, Zhao Chen, Darvin Yi, Khushi Gupta, Vijay Badrinarayanan, Andrew Rabinovich
We present DeepPerimeter, a deep learning based pipeline for inferring a full indoor perimeter (i. e. exterior boundary map) from a sequence of posed RGB images.
no code implementations • 8 Dec 2018 • Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
We propose a self-supervised learning framework that uses unlabeled monocular video sequences to generate large-scale supervision for training a Visual Odometry (VO) frontend, a network which computes pointwise data associations across images.
no code implementations • 21 Jun 2018 • Ayan Sinha, Zhao Chen, Vijay Badrinarayanan, Andrew Rabinovich
We demonstrate gradient adversarial training for three different scenarios: (1) as a defense to adversarial examples we classify gradient tensors and tune them to be agnostic to the class of their corresponding example, (2) for knowledge distillation, we do binary classification of gradient tensors derived from the student or teacher network and tune the student gradient tensor to mimic the teacher's gradient tensor; and (3) for multi-task learning we classify the gradient tensors derived from different task loss functions and tune them to be statistically indistinguishable.
2 code implementations • ECCV 2018 • Zhao Chen, Vijay Badrinarayanan, Gilad Drozdov, Andrew Rabinovich
We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels.
27 code implementations • 20 Dec 2017 • Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision.
4 code implementations • ICML 2018 • Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, Andrew Rabinovich
Deep multitask networks, in which one neural network produces multiple predictive outputs, can offer better speed and performance than their single-task counterparts but are challenging to train properly.
no code implementations • 24 Jul 2017 • Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
The first network, MagicPoint, operates on single images and extracts salient 2D points.
1 code implementation • ICCV 2017 • Chen-Yu Lee, Vijay Badrinarayanan, Tomasz Malisiewicz, Andrew Rabinovich
This paper focuses on the task of room layout estimation from a monocular RGB image.
1 code implementation • 30 Nov 2016 • Debidatta Dwibedi, Tomasz Malisiewicz, Vijay Badrinarayanan, Andrew Rabinovich
We present a Deep Cuboid Detector which takes a consumer-quality RGB image of a cluttered scene and localizes all 3D cuboids (box-like objects).
8 code implementations • 13 Jun 2016 • Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
We present a deep convolutional neural network for estimating the relative homography between a pair of images.
Ranked #3 on Homography Estimation on PDS-COCO
4 code implementations • 15 Jun 2015 • Wei Liu, Andrew Rabinovich, Alexander C. Berg
When we add our proposed global feature, and a technique for learning normalization parameters, accuracy increases consistently even over our improved versions of the baselines.
Ranked #39 on Semantic Segmentation on PASCAL VOC 2012 test
1 code implementation • 5 Mar 2015 • Jonathan Malmaud, Jonathan Huang, Vivek Rathod, Nick Johnston, Andrew Rabinovich, Kevin Murphy
We present a novel method for aligning a sequence of instructions to a video of someone carrying out a task.
2 code implementations • 20 Dec 2014 • Scott Reed, Honglak Lee, Dragomir Anguelov, Christian Szegedy, Dumitru Erhan, Andrew Rabinovich
On MNIST handwritten digits, we show that our model is robust to label corruption.
no code implementations • 20 Dec 2014 • David Warde-Farley, Andrew Rabinovich, Dragomir Anguelov
We study the problem of large scale, multi-label visual recognition with a large number of possible classes.
79 code implementations • CVPR 2015 • Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich
We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014).
no code implementations • 19 Dec 2013 • Samy Bengio, Jeff Dean, Dumitru Erhan, Eugene Ie, Quoc Le, Andrew Rabinovich, Jonathon Shlens, Yoram Singer
Albeit the simplicity of the resulting optimization problem, it is effective in improving both recognition and localization accuracy.