Multi-view Relighting using a Geometry-Aware Network - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles ACM Transactions on Graphics Year : 2019

Multi-view Relighting using a Geometry-Aware Network

Abstract

We propose the first learning-based algorithm that can relight images in a plausible and controllable manner given multiple views of an outdoor scene. In particular, we introduce a geometry-aware neural network that utilizes multiple geometry cues (normal maps, specular direction, etc.) and source and target shadow masks computed from a noisy proxy geometry obtained by multi-view stereo. Our model is a three-stage pipeline: two subnetworks refine the source and target shadow masks, and a third performs the final relighting. Furthermore, we introduce a novel representation for the shadow masks, which we call RGB shadow images. They reproject the colors from all views into the shadowed pixels and enable our network to cope with inacuraccies in the proxy and the non-locality of the shadow casting interactions. Acquiring large-scale multi-view relighting datasets for real scenes is challenging, so we train our network on photorealistic synthetic data. At train time, we also compute a noisy stereo-based geometric proxy, this time from the synthetic renderings. This allows us to bridge the gap between the real and synthetic domains. Our model generalizes well to real scenes. It can alter the illumination of drone footage, image-based renderings, textured mesh reconstructions, and even internet photo collections.
Fichier principal
Vignette du fichier
Multi-view-Relighting.pdf (44.56 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02125095 , version 1 (10-05-2019)

Identifiers

Cite

Julien Philip, Michaël Gharbi, Tinghui Zhou, Alexei A Efros, George Drettakis. Multi-view Relighting using a Geometry-Aware Network. ACM Transactions on Graphics, In press, 38, ⟨10.1145/3306346.3323013⟩. ⟨hal-02125095⟩
434 View
229 Download

Altmetric

Share

Gmail Facebook X LinkedIn More