Public Datasets

You may need passwords to access the full datasets.
Please email me with Your name/affiliation, name/email of your supervisor (if you are a student).

Audio-Visual Scene Reproduction datasets

Dataset link

This is an audio-visual dataset for Immersive Audio-Visual Scene Reproduction using Semantic Scene Reconstruction from 360 Cameras.

The following data are available for 5 different spaces

- Original sound sources recorded in an anechoic chamber (Sweep sound, Gun shot, Clarinet and Speech)
- 360 stereo camera image pairs
- Estimated depth maps
- Reconstructed semantic 3D models
- Rendered sound samples

IMPART multi-modal/multi-view datasets

Dataset link

This is multi-modal/multi-view datasets created in a cooperation between University of Surrey and Double Negative within the EU FP7 IMPART project.

If you get a permission to access, multi-modal static/dynamic footage and 3D reconstructions for various indoor/outdoor scenes are provided.

- LIDAR scans
- Digital snapshots and reconstructed 3D models
- Spherical camera scans and reconstructed 3D models
- Xtion RGBD video sequence and reconstructed 3D models
- Fixed multiple HD camera sequences
- Free moving and nodal HD cameras
- GoPro 2.7K cameras
- Performers: 6 male and 1 female performers
- Actions: Basic single actions, sequential actions, interactive actions.

i3DPost multi-view human action datasets

Dataset link

This is multi-view/3D human action/interaction datasets created in a cooperation between University of Surrey and CERTH-ITI within the i3DPost project.

If you get a permission to access, the following datasets are provided.

- Multi-view datasets - Synchronised/uncompressed-HD 8 view image sequences of 13 actions of 8 people (104 total)
- Sample videos
Actors/Actresses: Man1, Woman1, Man2, Man3, Woman2, Man4, Man5, Man6,
Actions: Walk, Run, Jump, Bend, Hand-wave, Jump-in-place, Sit-StandUp, Run-fall, Walk-sit, Run-jump-walk, Handshake, Pull, Facial-expressions

Multi-view studio datasets

Dataset link

This is multi-view video sets captured in a studio at University of Surrey.

The following datasets are available

- JP - different dance routines
- Roxanne - different costumes and actions
- Synthetic - different people
- Dan - different actions in pairs (password for zip files: 4Dv1d30)
- Infantry - different actions (password for zip files: 4Dv1d30)
- Knight - different actions (password for zip files: 4Dv1d30)