Path replay backpropagation: Differentiating light paths using constant memory and linear time

D Vicini, S Speierer, W Jakob - ACM Transactions on Graphics (TOG), 2021 - dl.acm.org
Differentiable physically-based rendering has become an indispensable tool for solving
inverse problems involving light. Most applications in this area jointly optimize a large set of …

Unbiased warped-area sampling for differentiable rendering

SP Bangaru, TM Li, F Durand - ACM Transactions on Graphics (TOG), 2020 - dl.acm.org
Differentiable rendering computes derivatives of the light transport equation with respect to
arbitrary 3D scene parameters, and enables various applications in inverse rendering and …

Monte Carlo estimators for differential light transport

T Zeltner, S Speierer, I Georgiev, W Jakob - ACM Transactions on …, 2021 - dl.acm.org
Physically based differentiable rendering algorithms propagate derivatives through realistic
light transport simulations and have applications in diverse areas including inverse …

Weakly-supervised contrastive learning in path manifold for monte carlo image reconstruction

IY Cho, Y Huo, SE Yoon - ACM Transactions on Graphics (TOG), 2021 - dl.acm.org
Image-space auxiliary features such as surface normal have significantly contributed to the
recent success of Monte Carlo (MC) reconstruction networks. However, path-space features …

Path tracing estimators for refractive radiative transfer

A Pediredla, YK Chalmiani, MG Scopelliti… - ACM Transactions on …, 2020 - dl.acm.org
Rendering radiative transfer through media with a heterogeneous refractive index is
challenging because the continuous refractive index variations result in light traveling along …

Unbiased and consistent rendering using biased estimators

Z Misso, B Bitterli, I Georgiev, W Jarosz - ACM Transactions on Graphics …, 2022 - dl.acm.org
We introduce a general framework for transforming biased estimators into unbiased and
consistent estimators for the same quantity. We show how several existing unbiased and …

Manifold path guiding for importance sampling specular chains

Z Fan, P Hong, J Guo, C Zou, Y Guo… - ACM Transactions on …, 2023 - dl.acm.org
Complex visual effects such as caustics are often produced by light paths containing
multiple consecutive specular vertices (dubbed specular chains), which pose a challenge to …

Unbiased caustics rendering guided by representative specular paths

H Li, B Wang, C Tu, K Xu, N Holzschuch… - SIGGRAPH Asia 2022 …, 2022 - dl.acm.org
Caustics are interesting patterns caused by the light being focused when reflecting off glossy
materials. Rendering them in computer graphics is still challenging: they correspond to high …

Efficient caustics rendering via spatial and temporal path reuse

X Xu, L Wang, B Wang - Computer Graphics Forum, 2023 - Wiley Online Library
Caustics are complex optical effects caused by the light being concentrated in a small area
due to reflection or refraction on surfaces with low roughness, typically under a sharp light …

[PDF][PDF] Slope-space integrals for specular next event estimation.

G Loubet, T Zeltner… - ACM Trans …, 2020 - rgl.s3.eu-central-1.amazonaws.com
This document provides additional derivations concerning integration and sampling of GGX
distribution on polygonal domains, building up to C++ fragments. We also include a brief …