Image-Based Rendering of Cars using Semantic Labels and Approximate Reflection Flow - Inria - Institut national de recherche en sciences et technologies du numérique
Journal Articles Proceedings of the ACM on Computer Graphics and Interactive Techniques Year : 2020

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

Abstract

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.
Fichier principal
Vignette du fichier
rodriguez2020-ibr-cars-semantic-and-reflection.pdf (15.74 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02533190 , version 1 (06-04-2020)

Identifiers

Cite

Simon Rodriguez, Siddhant Prakash, Peter Hedman, George Drettakis. Image-Based Rendering of Cars using Semantic Labels and Approximate Reflection Flow. Proceedings of the ACM on Computer Graphics and Interactive Techniques, 2020, 3, ⟨10.1145/3384535⟩. ⟨hal-02533190⟩
161 View
151 Download

Altmetric

Share

More