Page under construction!
The copyright for all of this data is owned by The Centre for Vision, Speech and Signal Processing, University of Surrey, UK. Permission is hereby granted to use the data for academic purposes only, provided that it is referenced in publications related to its use as mentioned in respective sections.
Dense Rigid Reconstruction from Unstructured Discontinuous Video
If using any of this data in an academic publication, please cite the following article: K. Lebeda, S. Hadfield, and R. Bowden: Dense rigid reconstruction from unstructured discontinuous video. In Proceedings of the ICCV workshop on 3D Representation and Recognition, 2015.
High quality supplementary videos: A: selected sequences overlaid with projected final model, B: selected partial reconstructions (progressive) and final model, C: selected partial reconstructions from individual subsequences, D: reconstructions on sequences from literature.
Input sequence: hillclimb.zip.
Direct-from-video: Unsupervised NRSfM
If using any of this data in an academic publication, please cite the following article: K. Lebeda, S. Hadfield and R. Bowden: Direct-from-Video: Unsupervised NRSfM. In Proceedings of the ECCV workshop on Recovering 6D Object Pose, 2016.
High quality supplementary videos: A: modelling results, B: space of basis shapes, C: number of basis shapes, D: shape changes.
Synthetic input sequence: cubicGlobe.avi, cubicGlobe.zip (jpg), ground truth depth, 16bit depth.