Image-Based Rendering of Cars using Semantic Labels and Approximate Reflection Flow

Image-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.

@Article{RPHD20,
  author       = "Rodriguez, Simon and Prakash, Siddhant and Hedman, Peter and Drettakis, George",
  title        = "Image-Based Rendering of Cars using Semantic Labels and Approximate Reflection Flow",
  journal      = "Proceedings of the ACM on Computer Graphics and Interactive Techniques",
  number       = "1",
  volume       = "3",
  month        = "may",
  year         = "2020",
  keywords     = "image-based rendering, semantic labeling, reflection rendering",
  url          = "http://www-sop.inria.fr/reves/Basilic/2020/RPHD20"
}