Publication
Mitsuba 2: A Retargetable Forward and Inverse Renderer
Related publications (77)
Differentiable Physically Based Rendering: Algorithms, Systems and Applications
Physically based rendering methods can create photorealistic images by simulating the propagation and interaction of light in a virtual scene. Given a scene description including the shape of objects, participating media, material properties, etc., the sim ...
EPFL2022Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering
Wenzel Alban Jakob, Nicolas Julien Roussel, Delio Aleardo Vicini, Sébastien Nicolas Speierer
Dr.Jit is a new just-in-time compiler for physically based rendering and its derivative. Dr.Jit expedites research on these topics in two ways: first, it traces high-level simulation code (e.g., written in Python) and aggressively simplifies and specialize ...
ASSOC COMPUTING MACHINERY2022Scene Decomposition and Relighting from Image Collections in Neural Rendering
The focus of our research is to generate controllable photo-realistic images of real-world scenes from existing observations, i.e., the inverse rendering problem. The approaches we focus on are those through neural rendering, utilizing neural network to de ...
2022Sub-micrometer morphology of human atherosclerotic plaque revealed by synchrotron radiation-based mu CT-A comparison with histology
Histology is a long standing and well-established gold standard for pathological characterizations. In recent years however, synchrotron radiation-based micro-computed tomography (SR mu CT) has become a tool for extending the imaging of two-dimensional thi ...
PUBLIC LIBRARY SCIENCE2022Light Path Gradients for Forward and Inverse Rendering
Physically based rendering is a process for photorealistic digital image synthesis and one of the core problems in computer graphics. It involves simulating the light transport, i.e. the emission, propagation, and scattering of light through a virtual scen ...
EPFL2021Path Replay Backpropagation: Differentiating Light Paths using Constant Memory and Linear Time
Wenzel Alban Jakob, Delio Aleardo Vicini, Sébastien Nicolas Speierer
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 scene parameters to minimize an objective function, in which case revers ...
ASSOC COMPUTING MACHINERY2021Perceptual Quality of Point Clouds with application to Compression
Modern information technologies and human-centric communication systems employ advanced content representations for richer portrayals of the real world. The newly adopted imaging modalities offer additional information cues and permit the depiction of real ...
EPFL2021A Non-Exponential Transmittance Model for Volumetric Scene Representations
Wenzel Alban Jakob, Delio Aleardo Vicini
We introduce a novel transmittance model to improve the volumetric representation of 3D scenes. The model can represent opaque surfaces in the volumetric light transport framework. Volumetric representations are useful for complex scenes, and become increa ...
ASSOC COMPUTING MACHINERY2021Monte Carlo Estimators for Differential Light Transport
Wenzel Alban Jakob, Tizian Lucien Zeltner, Sébastien Nicolas Speierer
Physically based differentiable rendering algorithms propagate derivatives through realistic light transport simulations and have applications in diverse areas including inverse reconstruction and machine learning. Recent progress has led to unbiased metho ...
ASSOC COMPUTING MACHINERY2021Raytraverse: Navigating the Lightfield to Enhance Climate-Based Daylight Modeling
Marilyne Andersen, Jan Wienold, Stephen William Wasilewski
We propose a new method for climate-based daylight modeling (CBDM) based on simulating and evaluating only the most important features. By adaptively sampling the temporal lightfield that describes daylight in buildings, our method escapes the curse of dim ...
2021