Natural Scenes Datasets for Exploration In 6DOF Navigation

Depth Image-Based Rendering (DIBR) and 6 Degrees-of-Freedom (6DoF) navigation are actually very active fields for immersive video, where the availability of common test conditions is mandatory to compare results. For this purpose, we propose different datasets to evaluate a wide range of tools needed by free navigation: a high-density HD image set, composed of 80k camera positions covering the entire 3D space, necessary to simulate all the head rotations and translations of a common user, and a UHD video set, composed of two sequences acquired with 3 by 5 cameras array. All the processing pipeline to obtain quality results is also detailed.

[1]  Atanas Gotchev,et al.  3D Visual Content Creation, Coding and Delivery , 2019 .

[2]  Touradj Ebrahimi,et al.  New Light Field Image Dataset , 2016, QoMEX 2016.

[3]  Christopher Joseph Pal,et al.  Learning Conditional Random Fields for Stereo , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Gauthier Lafruit,et al.  Free Navigation in Natural Scenery With DIBR: RVS and VSRS in MPEG-I Standardization , 2018, 2018 International Conference on 3D Immersion (IC3D).

[5]  Gauthier Lafruit,et al.  DEPTH IMAGE BASED VIEW SYNTHESIS WITH MULTIPLE REFERENCE VIEWS FOR VIRTUAL REALITY , 2018, 2018 - 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON).

[6]  Frédéric Dufaux,et al.  Subjective evaluation of Super Multi-View compressed contents on high-end light-field 3D displays , 2015 .