Wenzel Jakob

Wenzel Jakob

Auto-generated profile, based on publicly available information

Wenzel Jakob

EPFL, Lausanne, Switzerland

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2020 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
GRGilles Rainer
Gilles Rainer
AGAbhijeet Ghosh
Abhijeet Ghosh
WJWenzel Jakob
Wenzel Jakob
TWTim Weyrich
Tim Weyrich

22 July 2022 in ACM Transactions on Graphics
Verified
Journal Article
Open access
MNMerlin Nimier-David
Merlin Nimier-David
TMThomas Müller
Thomas Müller
AKAlexander Keller
Alexander Keller
WJWenzel Jakob
Wenzel Jakob
Volumetric representations are popular in inverse rendering because they have a simple parameterization, are smoothly varying, and transparently handle topology changes. However, incorporating the full volumetric transport of light is costly and challenging, often leading practitioners to implement simplified models, such as purely emissive and absorbing volumes with "baked" lighting. One such challenge is the efficient estimation of the gradients of the volume's appearance with respect to its scattering and absorption parameters. We show that the straightforward approach---differentiating a volumetric free-flight sampler---can lead to biased and high-variance gradients, hindering optimization. Instead, we propose using a new sampling strategy: differential ratio tracking , which is unbiased, yields low-variance gradients, and runs in linear time. Differential ratio tracking combines ratio tracking and reservoir sampling to estimate gradients by sampling distances proportional to the unweighted transmittance rather than the usual extinction-weighted transmittance. In addition, we observe local minima when optimizing scattering parameters to reproduce dense volumes or surfaces. We show that these local minima can be overcome by bootstrapping the optimization from nonphysical emissive volumes that are easily optimized.

26 July 2023 in ACM Transactions on Graphics
Verified
Journal Article
Open access
BNBaptiste Nicolet
Baptiste Nicolet
FRFabrice Rousselle
Fabrice Rousselle
JNJan Novak
Jan Novak
AKAlexander Keller
Alexander Keller
WJWenzel Jakob
Wenzel Jakob
TMThomas Müller
Thomas Müller
We present a method for reducing errors---variance and bias---in physically based differentiable rendering (PBDR). Typical applications of PBDR repeatedly render a scene as part of an optimization loop involving gradient descent. The actual change introduced by each gradient descent step is often relatively small, causing a significant degree of redundancy in this computation. We exploit this redundancy by formulating a gradient estimator that employs a recursive control variate , which leverages information from previous optimization steps. The control variate reduces variance in gradients, and, perhaps more importantly, alleviates issues that arise from differentiating loss functions with respect to noisy inputs, a common cause of drift to bad local minima or divergent optimizations. We experimentally evaluate our approach on a variety of path-traced scenes containing surfaces and volumes and observe that primal rendering efficiency improves by a factor of up to 10.

19 November 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
EYEkrem Fatih Yilmazer
Ekrem Fatih Yilmazer
DVDelio Vicini
Delio Vicini
WJWenzel Jakob
Wenzel Jakob
Partial differential equations can model diverse physical phenomena including heat diffusion, incompressible flows, and electrostatic potentials. Given a description of an object's boundary and interior, traditional methods solve such PDEs by densely meshing the interior and then solving a large and sparse linear system derived from this mesh. Recent grid-free solvers take an alternative approach and avoid this complexity in exchange for randomness: they compute stochastic solution estimates and generally bear a striking resemblance to physically-based rendering algorithms. In this article, we develop algorithms targeting the inverse form of this problem: given an already existing solution of a PDE, we infer parameters characterizing the boundary and interior. In the grid-free setting, there are again significant connections to rendering, and we show how insights from both fields can be combined to compute unbiased derivative estimates that enable gradient-based optimization. In this process, we encounter new challenges that must be addressed to obtain practical solutions. We introduce acceleration and variance reduction strategies and show how to differentiate branching random walks in reverse mode. We finally demonstrate our approach on both simulated data and a real-world electrical impedance tomography experiment, where we reconstruct the position of a conducting object from voltage measurements taken in a saline-filled tank.

19 November 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
BNBaptiste Nicolet
Baptiste Nicolet
FWFelix Wechsler
Felix Wechsler
JMJorge Madrid-Wolff
Jorge Madrid-Wolff
CMChristophe Moser
Christophe Moser
WJWenzel Jakob
Wenzel Jakob
Tomographic Volumetric Additive Manufacturing (TVAM) is an emerging 3D printing technology that can create complex objects in under a minute. The key idea is to project intense light patterns onto a rotating vial of photo-sensitive resin, causing polymerization where the cumulative dose of these patterns reaches the polymerization threshold. We formulate the pattern calculation as an inverse light transport problem and solve it via physically based differentiable rendering. In doing so, we address longstanding limitations of prior work by accurately modeling and correcting for scattering in composite resins, printing in non-symmetric vials, and supporting unusual printing geometries. We also introduce an improved discretization scheme that exploits the ray tracing operation to mitigate resolution-related artifacts in prints. We demonstrate the benefits of our method in real-world experiments, where our computed patterns produce prints with an improved fidelity.

20 July 2020 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
SDStavros Diolatzis
Stavros Diolatzis
AGAdrien Gruson
Adrien Gruson
WJWenzel Jakob
Wenzel Jakob
DNDerek Nowrouzezahrai
Derek Nowrouzezahrai
GDGeorge Drettakis
George Drettakis