Predicting Surface Reflectance Properties of Outdoor Scenes Under Unknown Natural Illumination

  title={Predicting Surface Reflectance Properties of Outdoor Scenes Under Unknown Natural Illumination},
  author={Farhan Rahman Wasee and Alen Joy and Charalambos (Charis) Poullis},
  journal={IEEE computer graphics and applications},
Estimating and modelling the appearance of an object under outdoor illumination conditions is a complex process. Although there have been several studies on illumination estimation and relighting, very few of them focus on estimating the reflectance properties of outdoor objects and scenes. This paper addresses this problem and proposes a complete framework to predict surface reflectance properties of outdoor scenes under unknown natural illumination. Uniquely, we recast the problem into its… 

Figures and Tables from this paper


Digitizing the Parthenon: Estimating Surface Reflectance Properties of a Complex Scene under Captured Natural Illumination
A process for estimating spatially-varying surface reflectance of a complex scene observed under natural illumination conditions is presented, showing that the technique can produce novel illumination renderings consistent with real photographs as well as reflectance properties that are consistent with ground-truth reflectance measurements.
Inverse global illumination: recovering reflectance models of real scenes from photographs
A lighting-independent model of the scene’s geometry and reflectance properties can be rendered with arbitrary modifications to structure and lighting via traditional rendering methods, and allows diffuse albedo to vary arbitrarily over surfaces while assuming that non-diffuse characteristics remain constant across particular regions.
Reflectance and Natural Illumination from a Single Image
A probabilistic formulation is introduced that seamlessly incorporates such constraints as priors to arrive at the maximum a posteriori estimates of reflectance and natural illumination.
Neural Illumination: Lighting Prediction for Indoor Environments
  • S. Song, T. Funkhouser
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
This paper proposes "Neural Illumination," a new approach that decomposes illumination prediction into several simpler differentiable sub-tasks: 1) geometry estimation, 2) scene completion, and 3) LDR-to-HDR estimation.
Deep Reflectance Maps
A convolutional neural architecture to estimate reflectance maps of specular materials in natural lighting conditions is proposed in an end-to-end learning formulation that directly predicts a reflectance map from the image itself.
Inverse Path Tracing for Joint Material and Lighting Estimation
A novel optimization method using a differentiable Monte Carlo renderer that computes derivatives with respect to the estimated unknown illumination and material properties enables joint optimization for physically correct light transport and material models using a tailored stochastic gradient descent.
Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image
A deep inverse rendering framework for indoor scenes, which combines novel methods to map complex materials to existing indoor scene datasets and a new physically-based GPU renderer to create a large-scale, photorealistic indoor dataset.
Learning to predict indoor illumination from a single image
An end-to-end deep neural network is trained that directly regresses a limited field-of-view photo to HDR illumination, without strong assumptions on scene geometry, material properties, or lighting, which allows to automatically recover high-quality HDR illumination estimates that significantly outperform previous state- of-the-art methods.
Deep Outdoor Illumination Estimation
It is demonstrated that the approach allows the recovery of plausible illumination conditions and enables photorealistic virtual object insertion from a single image and significantly outperforms previous solutions to this problem.
A Lightweight Approach for On-the-Fly Reflectance Estimation
This paper proposes a lightweight approach for surface reflectance estimation directly from 8-bit RGB images in real-time, which can be easily plugged into any 3D scanning-and-fusion system with a commodity RGBD sensor, and outperforms prior work forreflectance estimation in uncontrolled environments.