Physically Based Rendering: From Theory to Implementation

By M. Pharr, Greg Humphreys. 2004

2,125 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/9903e6c9c6462b91e37cc64ec161c88f20f2ba58

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset (2018, background): “Those lighting setups include information of lighting type (SunLight, SpotLight and AreaLight), energy, maximum distance (like PBRT -v3 [22]), position, direction and brightness, which are provided by manufacturers and have been aligned and ﬁxed to speciﬁc objects with lighting sources e.g. lamps.”
Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars (2017, methodology): “By computing both the reﬂected and transmitted components of rays in a physically accurate way, while conserving energies and obeying refraction equations, PBR photorealistically renders shadows, reﬂections, and refractions, thereby synthesizing superior levels of visual detail compared to other sha”
FastNeRF: High-Fidelity Neural Rendering at 200FPS (2021, background): “Given its practical importance, evaluating this integral efficiently has been a subject of active research for over three decades [9, 42, 8, 33].”
BOP Challenge 2020 on 6D Object Localization (2020, background): “This naturally accounts for complex illumination effects such as scattering, refraction and reflection, including diffuse and specular interreflection between the scene elements [41].”
Interactive procedural street modeling (2008, methodology): “We make use of stochastic sampling using Halton sequences [Pharr and Humphreys 2004] to create these patterns.”
Embree (2014, methodology): “The design of this path tracer broadly follows that of PBRT [Pharr and Humphreys 2004], and includes the renderer itself, integrators, samplers, materials, and BRDFs.”
Photographic Image Synthesis with Cascaded Refinement Networks (2017, background): “A system that synthesizes photorealistic images from semantic layouts would in effect function as a kind of rendering engine that bypasses the laborious specification of detailed threedimensional geometry and surface reflectance distributions, and avoids computationally intensive light transport sim”
DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition (2017, background): “Even though not all models come with realistic textures, the results quality highly depends on such characteristics—especially their reflectance (physically based rendering model [36] or bidirectional reflectance distribution function [40]).”
Exposing Digital Forgeries in Complex Lighting Environments (2007, methodology): “The synthetic images were rendered using the pbrt environment [17] with data from a gallery of light probe images maintained by Paul Debevec [18].”
Crowdsourcing in Computer Vision (2016, unknown): “To avoid this, the pattern can be offset by a different toroidal shift (Cranley-Patterson rotation [26]) in each pixel, or the digits of the sample points can be scrambled [89, 68, 96] by a different permutation (which is a simple bit-wise xor in some cases) in each pixel.”
3D Pictorial Structures for Multiple View Articulated Pose Estimation (2013, methodology): “Rotation Discretization We use best-candidate sampling [13] to generate a discrete set of rotations ΩR that are evenly spread.”
NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis (2020, methodology): “…recover full 3D models for graphics applications [57] fall under the second category, and use 3D geometry obtained from active scanning [37, 47, 61], proxy models [7, 10, 11], sil-houette masks [35, 58], or multiview stereo [33] as a starting point before recovering reﬂectance and reﬁned geometry.”
Enhancing Photorealism Enhancement (2021, background): “In the ensuing four decades, substantial further progress has been made, due in part to physically based simulation of light transport [2], principled representation ofmaterial appearance [3], [4], and photogrammetric modeling [5].”
Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications (2017, methodology): “For an in-depth introduction to path tracing and the plethora of techniques for reducing the computational complexity such as Monte Carlo importance sampling and efﬁcient data structures for accelerating the geometric computations, we refer the reader to the textbook by Pharr et al. [23].”
High Dynamic Range Imaging (2015, background): “In computer graphics, image rendering has always been one of the major goals, but just in mid-eighties researchers started to combine realistic image synthesis with physicallybased lighting simulation [63,119].”
ProcSy: Procedural Synthetic Dataset Generation Towards Influence Factor Studies Of Semantic Segmentation Networks (2019, methodology): “We leverage the idea of PBR materials and UE4’s metallic buffer output in order to label vehicle models as instance groups (i.e., all instances of a speciﬁc vehicle model have the same label).”