George Vogiatzis

Publications

• Multiview photometric stereo
• Overcoming shadows in 3-source photometric stereo
• DOMAIN ADAPTATION FOR REINFORCEMENT LEARNING ON THE ATARI
• Learning non-metric visual similarity for image retrieval
• Multi-camera Torso Pose Estimation using Graph Neural Networks
• Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines
• Dress like a star: Retrieving fashion products from videos
• How to read paintings: Semantic art understanding with multi-modal retrieval
• Learning an augmentation strategy for sparse datasets
• Using multiple hypotheses to improve depth-maps for multi-view stereo
• Shadows in three-source photometric stereo
• Asymmetric Spatio-Temporal Embeddings for Large-Scale Image-to-Video Retrieval
• Variational Recurrent Sequence-to-Sequence Retrieval for Stepwise Illustration
• Reconstructing relief surfaces
• Deep Reinforcement Learning for Autonomous Traffic Light Control
• A Deep Learning Pipeline for Semantic Facade Segmentation
• Learning Non-Metric Visual Similarity for Image Retrieval
• A probabilistic model for trust and reputation
• Video normals from colored lights
• A generative model for online depth fusion
• A Deep Learning Approach to Automatic Caption Generation for News Images
• Self-calibrated, multi-spectral photometric stereo for 3D face capture
• Live 3D shape reconstruction, recognition and registration
• Video-based, real-time multi-view stereo
• Automatic object segmentation from calibrated images
• Practical 3D reconstruction based on photometric stereo
• Optimization of facade segmentation based on layout priors
• Traffic3D
• How to read paintings
• Shape from photographs
• Multi-model fitting based on minimum spanning tree
• Large scale multi-view stereopsis evaluation
• Traffic3d
• Vehicle tire (tyre) detection and text recognition using deep learning
• Large-scale data for multiple-view stereopsis
• Neural Caption Generation for News Images
• QuiltGAN: An Adversarially Trained, Procedural Algorithm for Texture Generation
• Dress Like a Star
• Automatic 3D object segmentation in multiple views using volumetric graph-cuts
• Fully-Autonomous, Vision-based Traffic Signal Control: from Simulation to Reality
• Domain adaptation for reinforcement learning on the Atari
• An Efficient Industrial System for Vehicle Tyre (Tire) Detection and Text Recognition Using Deep Learning
• Goal Density-based Hindsight Experience Prioritization for Multi-Goal Robot Manipulation Reinforcement Learning
• Multi-camera Torso Pose Estimation using Graph Neural Networks
• Non-rigid photometric stereo with colored light
• Multi-Agent Deep Reinforcement Learning for Traffic optimization through Multiple Road Intersections using Live Camera Feed
• Look and listen
• A Deep Reinforcement Learning Agent for Traffic Intersection Control Optimization
• CSC-GAN
• rcGAN: Learning a Generative Model for Arbitrary Size Image Generation
• Multiview stereo via volumetric graph-cuts and occlusion robust photo-consistency
• Probabilistic visibility for multi-view stereo
• Reconstruction in the round using photometric normals and silhouettes
• Using frontier points to recover shape, reflectance and illumination
• Multi-view stereo via volumetric graph-cuts
• Automatic 3D object segmentation in multiple views using volumetric graph-cuts
• Overcoming Shadows in 3-Source Photometric Stereo