CVSSP3D Publications and Datasets

Introduction

Over the last decade, the Visual Media Lab at the University of Surrey's Centre for Vision, Speech and Signal Processing have been researching methods to create interactive virtual characters from markerless multi-camera capture. This site gives an overview of the multiple camera datasets that have been made publically avaliable.

License

The datasets are free for research use only.

This agreement must be confirmed by a senior representative of your organisation. To access and use this data you agree to the following conditions:

• Multiple view video sets and associated data files will be used for research purposes only.
• The dataset source should be acknowledged in all publications and publicity material which it is used or results derived from the data are used by referencing the relevant publication as indicated for specific datasets and inclusion of the repository link
• The datasets should not be used for commercial purposes.
• The data should not be redistributed.

To request access to the CVSSP Dataset Repository, please contact: a.hilton@surrey.ac.uk

Publications

• Joint Demosaicing and Chromatic Aberration Correction of Images Using Neural Networks
• U4D: Unsupervised 4D Dynamic Scene Understanding
• Semantically Coherent 4D Scene Flow of Dynamic Scenes
• Hybrid Skeleton Driven Surface Registration for Temporally Consistent Volumetric Video
• Hybrid modelling of non-rigid scenes from RGBD cameras
• 4D Temporally Coherent Light-field Video
• Real-time Full-Body Motion Capture from Video and IMUs
• Total Capture: 3D Human Pose Estimation Fusing Video and Inertial Sensors
• Semantically Coherent Co-segmentation and Reconstruction of Dynamic Scenes
• 4D Match Trees for Non-rigid Surface Alignment
• Temporally coherent 4D reconstruction of complex dynamic scenes
• General Dynamic Scene Reconstruction from Multiple View Video
• Segmentation based features for wide-baseline multi-view reconstruction
• Hybrid Skeletal-Surface Motion Graphs for Character Animation from 4D Performance Capture
• 4D Model Flow: Precomputed Appearance Alignment for Real-time 4D Video
• Online Interactive 4D Character Animation
• Optimal Represenatation of Multi-View Video
• 4D Video Textures for Interactive Character Appearance
• Interactive Animation of 4D Performance Capture
• Global Non-rigid Alignment of Surface Sequences
• Surface Capture for Performance-Based Animation

Datasets