Soft 3D Reconstruction for View Synthesis
Events
Subscribe:  iCal  |  Google Calendar
7, Mar — 1, Jun
York US   26, Mar — 29, Mar
Boston US   28, Mar — 1, Apr
Anaheim US   29, Mar — 1, Apr
RALEIGH US   30, Mar — 1, Apr
Latest comments

Those animations look amazing!! Great job!

Very cool review of the making of Spellbreak. Would be even more cool to see some videos inside UE4 showing how they do a few very specific things unique to them.

This was so helpful for me. I'm hoping to adapt your tutorial to pull off something similar comparing modern satellite imagery with historical maps. No topo, so my steps should be simpler, but I'm a novice with Blender and you've really helped. Thanks!

Soft 3D Reconstruction for View Synthesis
11 October, 2017
News

Eric Penner and Li Zhang from Google revealed a novel algorithm for view synthesis that utilizes a soft 3D reconstruction to improve quality, continuity and robustness. The thing is that the new algorithm means more details and less artifacts. 

Our main contribution is the formulation of a soft 3D representation that preserves depth uncertainty through each stage of 3D reconstruction and rendering. We show that this representation is beneficial throughout the view synthesis pipeline. During view synthesis, it provides a soft model of scene geometry that provides continuity across synthesized views and robustness to depth uncertainty.

During 3D reconstruction, the same robust estimates of scene visibility can be applied iteratively to improve depth estimation around object edges. Our algorithm is based entirely on O(1) filters, making it conducive to acceleration and it works with structured or unstructured sets of input views. We compare with recent classical and learning-based algorithms on plenoptic lightfields, wide baseline captures, and lightfield videos produced from camera arrays.

Eric Penner and Li Zhang 

You can find more details on the project and read the paper here.  

Leave a Reply

avatar