Lighting Estimation

15 papers with code • 0 benchmarks • 0 datasets

Lighting Estimation analyzes given images to provide detailed information about the lighting in a scene.

Most implemented papers

Deep Parametric Indoor Lighting Estimation

WinterCyan/Gardner2019 ICCV 2019

We present a method to estimate lighting from a single image of an indoor scene.

Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination

pratulsrinivasan/lighthouse CVPR 2020

We present a deep learning solution for estimating the incident illumination at any 3D location within a scene from an input narrow-baseline stereo image pair.

PointAR: Efficient Lighting Estimation for Mobile Augmented Reality

cake-lab/PointAR ECCV 2020

We propose an efficient lighting estimation pipeline that is suitable to run on modern mobile devices, with comparable resource complexities to state-of-the-art mobile deep learning models.

Deep Lighting Environment Map Estimation from Spherical Panoramas

VCL3D/DeepPanoramaLighting 16 May 2020

We approach this problem differently, exploiting the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism.

Shape From Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing

brownvc/shapefromtracing 6 Dec 2020

In this paper, we explore how to use differentiable ray tracing to refine an initial coarse mesh and per-mesh-facet material representation.

GMLight: Lighting Estimation via Geometric Distribution Approximation

fnzhan/Illumination-Estimation 20 Feb 2021

This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation.

Xihe: A 3D Vision-based Lighting Estimation Framework for Mobile Augmented Reality

cake-lab/Xihe 30 May 2021

Centering the key idea of 3D vision, in this work, we design an edge-assisted framework called Xihe to provide mobile AR applications the ability to obtain accurate omnidirectional lighting estimation in real time.

NeILF: Neural Incident Light Field for Physically-based Material Estimation

apple/ml-neilf 14 Mar 2022

We present a differentiable rendering framework for material and lighting estimation from multi-view images and a reconstructed geometry.

DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images

lei-wang-github/DeepPS2 5 Jul 2022

Despite the success of existing traditional and deep learning-based methods, it is still challenging due to: (i) the requirement of three or more differently illuminated images, (ii) the inability to model unknown general reflectance, and (iii) the requirement of accurate 3D ground truth surface normals and known lighting information for training.

StyleLight: HDR Panorama Generation for Lighting Estimation and Editing

wanggcong/stylelight 29 Jul 2022

To tackle this problem, we propose a coupled dual-StyleGAN panorama synthesis network (StyleLight) that integrates LDR and HDR panorama synthesis into a unified framework.