Mitsuba 2: A retargetable forward and inverse renderer

M Nimier-David, D Vicini, T Zeltner… - ACM Transactions on …, 2019‏ - dl.acm.org
Modern rendering systems are confronted with a dauntingly large and growing set of
requirements: in their pursuit of realism, physically based techniques must increasingly …

Differentiable monte carlo ray tracing through edge sampling

TM Li, M Aittala, F Durand, J Lehtinen - ACM Transactions on Graphics …, 2018‏ - dl.acm.org
Gradient-based methods are becoming increasingly important for computer graphics,
machine learning, and computer vision. The ability to compute gradients is crucial to …

Spatiotemporal reservoir resampling for real-time ray tracing with dynamic direct lighting

B Bitterli, C Wyman, M Pharr, P Shirley… - ACM Transactions on …, 2020‏ - dl.acm.org
Efficiently rendering direct lighting from millions of dynamic light sources using Monte Carlo
integration remains a challenging problem, even for off-line rendering systems. We …

[كتاب][B] Path-space differentiable rendering

C Zhang - 2022‏ - search.proquest.com
Abstract Physics-based differentiable rendering---which is concerned with estimating
derivatives of photorealistic rendering with respect to arbitrary scene parameters---has a …

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 …

A differential theory of radiative transfer

C Zhang, L Wu, C Zheng, I Gkioulekas… - ACM Transactions on …, 2019‏ - dl.acm.org
Physics-based differentiable rendering is the task of estimating the derivatives of radiometric
measures with respect to scene parameters. The ability to compute these derivatives is …

Differentiable rendering of neural sdfs through reparameterization

SP Bangaru, M Gharbi, F Luan, TM Li… - SIGGRAPH Asia 2022 …, 2022‏ - dl.acm.org
We present a method to automatically compute correct gradients with respect to geometric
scene parameters in neural SDF renderers. Recent physically-based differentiable …

A new hybrid seagull optimization algorithm for feature selection

H Jia, Z **ng, W Song - IEEE access, 2019‏ - ieeexplore.ieee.org
Hybrid algorithms have attracted more and more attention in the field of optimization
algorithms. In this paper, three hybrid algorithms are proposed to solve feature selection …

Learning to importance sample in primary sample space

Q Zheng, M Zwicker - Computer Graphics Forum, 2019‏ - Wiley Online Library
Importance sampling is one of the most widely used variance reduction strategies in Monte
Carlo rendering. We propose a novel importance sampling technique that uses a neural …

Risp: Rendering-invariant state predictor with differentiable simulation and rendering for cross-domain parameter estimation

P Ma, T Du, JB Tenenbaum, W Matusik… - arxiv preprint arxiv …, 2022‏ - arxiv.org
This work considers identifying parameters characterizing a physical system's dynamic
motion directly from a video whose rendering configurations are inaccessible. Existing …