Search Results for author: Simon Stent

Found 18 papers, 10 papers with code

SceneNet: Understanding Real World Indoor Scenes With Synthetic Data

1 code implementation22 Nov 2015 Ankur Handa, Viorica Patraucean, Vijay Badrinarayanan, Simon Stent, Roberto Cipolla

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments.

Scene Understanding

Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation

no code implementations6 Apr 2016 German Ros, Simon Stent, Pablo F. Alcantarilla, Tomoki Watanabe

In this work we investigate the problem of road scene semantic segmentation using Deconvolutional Networks (DNs).

Semantic Segmentation

Understanding Real World Indoor Scenes With Synthetic Data

no code implementations CVPR 2016 Ankur Handa, Viorica Patraucean, Vijay Badrinarayanan, Simon Stent, Roberto Cipolla

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments.

Scene Understanding

gvnn: Neural Network Library for Geometric Computer Vision

1 code implementation25 Jul 2016 Ankur Handa, Michael Bloesch, Viorica Patraucean, Simon Stent, John McCormac, Andrew Davison

We introduce gvnn, a neural network library in Torch aimed towards bridging the gap between classic geometric computer vision and deep learning.

Image Reconstruction Visual Odometry

A Dataset To Evaluate The Representations Learned By Video Prediction Models

1 code implementation25 Feb 2018 Ryan Szeto, Simon Stent, German Ros, Jason J. Corso

We present a parameterized synthetic dataset called Moving Symbols to support the objective study of video prediction networks.

Video Prediction

Street-view change detection with deconvolutional networks

no code implementations Autonomous Robots 2018 Pablo F. Alcantarilla, Simon Stent, Germán Ros, Roberto Arroyo, Riccardo Gherardi

We propose a system for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time.

3D Reconstruction Change Detection +2

Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks

1 code implementation ECCV 2018 Adrià Recasens, Petr Kellnhofer, Simon Stent, Wojciech Matusik, Antonio Torralba

We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task.

Caricature Gaze Estimation +2

LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision

no code implementations ICCV 2021 Zhijian Liu, Simon Stent, Jie Li, John Gideon, Song Han

Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets.

Image Classification Instance Segmentation +3

MAAD: A Model and Dataset for "Attended Awareness" in Driving

1 code implementation16 Oct 2021 Deepak Gopinath, Guy Rosman, Simon Stent, Katsuya Terahata, Luke Fletcher, Brenna Argall, John Leonard

Our model takes as input scene information in the form of a video and noisy gaze estimates, and outputs visual saliency, a refined gaze estimate, and an estimate of the person's attended awareness.

Denoising

The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video

1 code implementation ICCV 2021 John Gideon, Simon Stent

The ability to reliably estimate physiological signals from video is a powerful tool in low-cost, pre-clinical health monitoring.

Contrastive Learning Image-Variation

Revealing Occlusions with 4D Neural Fields

no code implementations CVPR 2022 Basile Van Hoorick, Purva Tendulka, Didac Suris, Dennis Park, Simon Stent, Carl Vondrick

For computer vision systems to operate in dynamic situations, they need to be able to represent and reason about object permanence.

Video Understanding

Shadows Shed Light on 3D Objects

no code implementations17 Jun 2022 Ruoshi Liu, Sachit Menon, Chengzhi Mao, Dennis Park, Simon Stent, Carl Vondrick

Experiments and visualizations show that the method is able to generate multiple possible solutions that are consistent with the observation of the shadow.

3D Reconstruction Object +1

CW-ERM: Improving Autonomous Driving Planning with Closed-loop Weighted Empirical Risk Minimization

1 code implementation5 Oct 2022 Eesha Kumar, Yiming Zhang, Stefano Pini, Simon Stent, Ana Ferreira, Sergey Zagoruyko, Christian S. Perone

The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states.

Autonomous Driving Imitation Learning

What You Can Reconstruct From a Shadow

no code implementations CVPR 2023 Ruoshi Liu, Sachit Menon, Chengzhi Mao, Dennis Park, Simon Stent, Carl Vondrick

Experiments and visualizations show that the method is able to generate multiple possible solutions that are consistent with the observation of the shadow.

3D Reconstruction Object +1

Tracking through Containers and Occluders in the Wild

1 code implementation CVPR 2023 Basile Van Hoorick, Pavel Tokmakov, Simon Stent, Jie Li, Carl Vondrick

Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems.

Visual Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.