Title
Image-Based Rendering of Cars using Semantic Labels and Approximate Reflection Flow
Abstract
AbstractImage-Based Rendering (IBR) has made impressive progress towards highly realistic, interactive 3D navigation for many scenes, including cityscapes. However, cars are ubiquitous in such scenes; multi-view stereo reconstruction provides proxy geometry for IBR, but has difficulty with shiny car bodies, and leaves holes in place of reflective, semi-transparent windows on cars. We present a new approach allowing free-viewpoint IBR of cars based on an approximate analytic reflection flow computation on curved windows. Our method has three components: a refinement step of reconstructed car geometry guided by semantic labels, that provides an initial approximation for missing window surfaces and a smooth completed car hull; an efficient reflection flow computation using an ellipsoid approximation of the curved car windows that runs in real-time in a shader and a reflection/background layer synthesis solution. These components allow plausible rendering of reflective, semi-transparent windows in free viewpoint navigation. We show results on several scenes casually captured with a single consumer-level camera, demonstrating plausible car renderings with significant improvement in visual quality over previous methods.
Year
DOI
Venue
2020
10.1145/3384535
Proceedings of the ACM on Computer Graphics and Interactive Techniques
Keywords
DocType
Volume
Rendering (computer graphics),Image-based modeling and rendering,Shader,Computer graphics (images),Ellipsoid,Computer science,Hull,Flow computation,Interactive 3d,Stereo reconstruction
Journal
3
Issue
Citations 
PageRank 
1
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Simon Rodriguez100.68
Siddhant Prakash201.01
peter hedman3816.63
George Drettakis42281147.82