Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Roberto Cipolla

Roberto Cipolla

X-MAN: Explaining multiple sources of anomalies in video


Jun 16, 2021
Stanislaw Szymanowicz, James Charles, Roberto Cipolla

Figure 1 for X-MAN: Explaining multiple sources of anomalies in video
Figure 2 for X-MAN: Explaining multiple sources of anomalies in video
Figure 3 for X-MAN: Explaining multiple sources of anomalies in video
Figure 4 for X-MAN: Explaining multiple sources of anomalies in video
* In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2021 
  Access Paper or Ask Questions

LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo


Apr 27, 2021
Roberto Mecca, Fotios Logothetis, Ignas Budvytis, Roberto Cipolla

Figure 1 for LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
Figure 2 for LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
Figure 3 for LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
Figure 4 for LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo

  Access Paper or Ask Questions

FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras


Apr 21, 2021
Anthony Hu, Zak Murez, Nikhil Mohan, Sofía Dudas, Jeff Hawke, Vijay Badrinarayanan, Roberto Cipolla, Alex Kendall

Figure 1 for FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
Figure 2 for FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
Figure 3 for FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
Figure 4 for FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras

  Access Paper or Ask Questions

Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild


Mar 30, 2021
Akash Sengupta, Ignas Budvytis, Roberto Cipolla

Figure 1 for Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
Figure 2 for Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
Figure 3 for Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
Figure 4 for Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
* Accepted at CVPR 2021, 16 pages, 8 figures 
  Access Paper or Ask Questions

Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild


Sep 22, 2020
Akash Sengupta, Ignas Budvytis, Roberto Cipolla

Figure 1 for Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
Figure 2 for Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
Figure 3 for Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
Figure 4 for Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
* 14 pages, 7 figures, BMVC 2020, Fixed abstract typos 
  Access Paper or Ask Questions

A CNN Based Approach for the Near-Field Photometric Stereo Problem


Sep 12, 2020
Fotios Logothetis, Ignas Budvytis, Roberto Mecca, Roberto Cipolla

Figure 1 for A CNN Based Approach for the Near-Field Photometric Stereo Problem
Figure 2 for A CNN Based Approach for the Near-Field Photometric Stereo Problem
Figure 3 for A CNN Based Approach for the Near-Field Photometric Stereo Problem
Figure 4 for A CNN Based Approach for the Near-Field Photometric Stereo Problem

  Access Paper or Ask Questions

Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments


Sep 11, 2020
Steven D. Morad, Roberto Mecca, Rudra P. K. Poudel, Stephan Liwicki, Roberto Cipolla

Figure 1 for Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
Figure 2 for Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
Figure 3 for Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
Figure 4 for Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments

  Access Paper or Ask Questions

PX-NET: Simple, Efficient Pixel-Wise Training of Photometric Stereo Networks


Aug 11, 2020
Fotios Logothetis, Ignas Budvytis, Roberto Mecca, Roberto Cipolla

Figure 1 for PX-NET: Simple, Efficient Pixel-Wise Training of Photometric Stereo Networks
Figure 2 for PX-NET: Simple, Efficient Pixel-Wise Training of Photometric Stereo Networks
Figure 3 for PX-NET: Simple, Efficient Pixel-Wise Training of Photometric Stereo Networks
Figure 4 for PX-NET: Simple, Efficient Pixel-Wise Training of Photometric Stereo Networks

  Access Paper or Ask Questions

Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop


Jul 21, 2020
Benjamin Biggs, Oliver Boyne, James Charles, Andrew Fitzgibbon, Roberto Cipolla

Figure 1 for Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
Figure 2 for Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
Figure 3 for Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
Figure 4 for Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
* Accepted at ECCV 2020 
  Access Paper or Ask Questions

Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks


Mar 30, 2020
Thomas Roddick, Roberto Cipolla

Figure 1 for Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks
Figure 2 for Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks
Figure 3 for Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks
Figure 4 for Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks

  Access Paper or Ask Questions

Learning a Spatio-Temporal Embedding for Video Instance Segmentation


Dec 19, 2019
Anthony Hu, Alex Kendall, Roberto Cipolla

Figure 1 for Learning a Spatio-Temporal Embedding for Video Instance Segmentation
Figure 2 for Learning a Spatio-Temporal Embedding for Video Instance Segmentation
Figure 3 for Learning a Spatio-Temporal Embedding for Video Instance Segmentation
Figure 4 for Learning a Spatio-Temporal Embedding for Video Instance Segmentation

  Access Paper or Ask Questions

Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression


Sep 23, 2019
Ignas Budvytis, Marvin Teichmann, Tomas Vojir, Roberto Cipolla

Figure 1 for Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression
Figure 2 for Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression
Figure 3 for Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression
Figure 4 for Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression
* BMVC 2019 
  Access Paper or Ask Questions

Orientation-aware Semantic Segmentation on Icosahedron Spheres


Jul 30, 2019
Chao Zhang, Stephan Liwicki, William Smith, Roberto Cipolla

Figure 1 for Orientation-aware Semantic Segmentation on Icosahedron Spheres
Figure 2 for Orientation-aware Semantic Segmentation on Icosahedron Spheres
Figure 3 for Orientation-aware Semantic Segmentation on Icosahedron Spheres
Figure 4 for Orientation-aware Semantic Segmentation on Icosahedron Spheres
* 9 pages, accepted to iccv 2019 
  Access Paper or Ask Questions

Fast-SCNN: Fast Semantic Segmentation Network


Feb 12, 2019
Rudra P K Poudel, Stephan Liwicki, Roberto Cipolla

Figure 1 for Fast-SCNN: Fast Semantic Segmentation Network
Figure 2 for Fast-SCNN: Fast Semantic Segmentation Network
Figure 3 for Fast-SCNN: Fast Semantic Segmentation Network
Figure 4 for Fast-SCNN: Fast Semantic Segmentation Network

  Access Paper or Ask Questions

Orthographic Feature Transform for Monocular 3D Object Detection


Nov 20, 2018
Thomas Roddick, Alex Kendall, Roberto Cipolla

Figure 1 for Orthographic Feature Transform for Monocular 3D Object Detection
Figure 2 for Orthographic Feature Transform for Monocular 3D Object Detection
Figure 3 for Orthographic Feature Transform for Monocular 3D Object Detection
Figure 4 for Orthographic Feature Transform for Monocular 3D Object Detection

  Access Paper or Ask Questions

Creatures great and SMAL: Recovering the shape and motion of animals from video


Nov 14, 2018
Benjamin Biggs, Thomas Roddick, Andrew Fitzgibbon, Roberto Cipolla

Figure 1 for Creatures great and SMAL: Recovering the shape and motion of animals from video
Figure 2 for Creatures great and SMAL: Recovering the shape and motion of animals from video
Figure 3 for Creatures great and SMAL: Recovering the shape and motion of animals from video
Figure 4 for Creatures great and SMAL: Recovering the shape and motion of animals from video
* 17 pages, ACCV 2018 oral paper 
  Access Paper or Ask Questions

A Differential Volumetric Approach to Multi-View Photometric Stereo


Nov 05, 2018
Fotios Logothetis, Roberto Mecca, Roberto Cipolla

Figure 1 for A Differential Volumetric Approach to Multi-View Photometric Stereo
Figure 2 for A Differential Volumetric Approach to Multi-View Photometric Stereo
Figure 3 for A Differential Volumetric Approach to Multi-View Photometric Stereo
Figure 4 for A Differential Volumetric Approach to Multi-View Photometric Stereo

  Access Paper or Ask Questions

Convolutional CRFs for Semantic Segmentation


May 15, 2018
Marvin T. T. Teichmann, Roberto Cipolla

Figure 1 for Convolutional CRFs for Semantic Segmentation
Figure 2 for Convolutional CRFs for Semantic Segmentation
Figure 3 for Convolutional CRFs for Semantic Segmentation
Figure 4 for Convolutional CRFs for Semantic Segmentation
* 8 Pages + Appendix, references. Code can be found under: https://github.com/MarvinTeichmann/ConvCRF 
  Access Paper or Ask Questions

MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving


May 08, 2018
Marvin Teichmann, Michael Weber, Marius Zoellner, Roberto Cipolla, Raquel Urtasun

Figure 1 for MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
Figure 2 for MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
Figure 3 for MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
Figure 4 for MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
* 9 pages, 7 tables and 9 figures; first place on Kitti Road Segmentation; Code on GitHub (https://github.com/MarvinTeichmann/MultiNet) 
  Access Paper or Ask Questions

Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics


Apr 24, 2018
Alex Kendall, Yarin Gal, Roberto Cipolla

Figure 1 for Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Figure 2 for Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Figure 3 for Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Figure 4 for Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
* CVPR 2018 
  Access Paper or Ask Questions

Geometric Loss Functions for Camera Pose Regression with Deep Learning


May 23, 2017
Alex Kendall, Roberto Cipolla

Figure 1 for Geometric Loss Functions for Camera Pose Regression with Deep Learning
Figure 2 for Geometric Loss Functions for Camera Pose Regression with Deep Learning
Figure 3 for Geometric Loss Functions for Camera Pose Regression with Deep Learning
Figure 4 for Geometric Loss Functions for Camera Pose Regression with Deep Learning
* CVPR 2017 
  Access Paper or Ask Questions

Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups


Nov 30, 2016
Yani Ioannou, Duncan Robertson, Roberto Cipolla, Antonio Criminisi

Figure 1 for Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
Figure 2 for Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
Figure 3 for Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
Figure 4 for Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
* Updated full version of paper, in full letter paper two-column paper. Includes many textual changes, updated CIFAR10 results, and new analysis of inter/intra-layer correlation 
  Access Paper or Ask Questions

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding


Oct 10, 2016
Alex Kendall, Vijay Badrinarayanan, Roberto Cipolla

Figure 1 for Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
Figure 2 for Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
Figure 3 for Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
Figure 4 for Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding

  Access Paper or Ask Questions

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation


Oct 10, 2016
Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla

Figure 1 for SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Figure 2 for SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Figure 3 for SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Figure 4 for SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

  Access Paper or Ask Questions

Spatio-temporal video autoencoder with differentiable memory


Sep 01, 2016
Viorica Patraucean, Ankur Handa, Roberto Cipolla

Figure 1 for Spatio-temporal video autoencoder with differentiable memory
Figure 2 for Spatio-temporal video autoencoder with differentiable memory
Figure 3 for Spatio-temporal video autoencoder with differentiable memory
Figure 4 for Spatio-temporal video autoencoder with differentiable memory
* The experiments section has been extended and a direct application to weakly-supervised video segmentation through label propagation has been included 
  Access Paper or Ask Questions

Refining Architectures of Deep Convolutional Neural Networks


Apr 22, 2016
Sukrit Shankar, Duncan Robertson, Yani Ioannou, Antonio Criminisi, Roberto Cipolla

Figure 1 for Refining Architectures of Deep Convolutional Neural Networks
Figure 2 for Refining Architectures of Deep Convolutional Neural Networks
Figure 3 for Refining Architectures of Deep Convolutional Neural Networks
Figure 4 for Refining Architectures of Deep Convolutional Neural Networks
* 9 pages, 6 figures, CVPR 2016 
  Access Paper or Ask Questions

PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization


Feb 18, 2016
Alex Kendall, Matthew Grimes, Roberto Cipolla

Figure 1 for PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
Figure 2 for PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
Figure 3 for PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
Figure 4 for PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
* 9 pages, 13 figures; Corrected numerical error in orientation results 
  Access Paper or Ask Questions

Modelling Uncertainty in Deep Learning for Camera Relocalization


Feb 18, 2016
Alex Kendall, Roberto Cipolla

Figure 1 for Modelling Uncertainty in Deep Learning for Camera Relocalization
Figure 2 for Modelling Uncertainty in Deep Learning for Camera Relocalization
Figure 3 for Modelling Uncertainty in Deep Learning for Camera Relocalization
Figure 4 for Modelling Uncertainty in Deep Learning for Camera Relocalization
* ICRA 2016; Fixed numerical error with rotation results 
  Access Paper or Ask Questions

Training CNNs with Low-Rank Filters for Efficient Image Classification


Feb 07, 2016
Yani Ioannou, Duncan Robertson, Jamie Shotton, Roberto Cipolla, Antonio Criminisi

Figure 1 for Training CNNs with Low-Rank Filters for Efficient Image Classification
Figure 2 for Training CNNs with Low-Rank Filters for Efficient Image Classification
Figure 3 for Training CNNs with Low-Rank Filters for Efficient Image Classification
Figure 4 for Training CNNs with Low-Rank Filters for Efficient Image Classification
* International Conference on Learning Representations (ICLR), San Juan, Puerto Rico, 2-4 May 2016 
 * Published as a conference paper at ICLR 2016. v3: updated ICLR status. v2: Incorporated reviewer's feedback including: Amend Fig. 2 and 5 descriptions to explain that there are no ReLUs within the figures. Fix headings of Table 5 - Fix typo in the sentence at bottom of page 6. Add ref. to Predicting Parameters in Deep Learning. Fix Table 6, GMP-LR and GMP-LR-2x had incorrect numbers of filters 
  Access Paper or Ask Questions