WJWojciech Jarosz

Wojciech Jarosz

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Wojciech Jarosz has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Geometric Antithetic Sampling for Rendering Spatiotemporally Modulated Light

    by Juhyeon Kim, Jack Cui, Wojciech Jarosz, Adithya Pediredla

  • Difference‐aware Filtering for Event Camera Simulation

    by Juhyeon Kim, Wojciech Jarosz, Adithya Pediredla

    We present EventSVGF, an event camera rendering framework based on spatiotemporal variance‐guided filtering (SVGF) [SKW*17], designed to achieve high temporal accuracy especially in high‐frequency regions, which is critical for faithful event simulation. Unlike conventional rendering, event cameras measure temporal changes in brightness (log‐intensity), requiring accurate estimation of per‐pixel, frame‐to‐frame differences. However, naively computing temporal differences from primal‐domain RGB images leads to severe noise, as existing denoising methods are designed for primal signals rather than their differences. Our key contribution is a method that directly denoises the pixel‐wise temporal difference signal using correlated sampling, formulated as a difference‐aware extension of the SVGF pipeline, termed EventSVGF. EventSVGF incorporates a novel edge‐stopping function, an adapted temporal accumulation scheme, and an albedo demodulation strategy, all tailored for accurate event camera simulation. Our method achieves stable results at low sampling rates (2 spp), whereas existing approaches typically require significantly higher sampling budgets (32–512 spp). We demonstrate EventSVGF on dynamic scenes, showing improved accuracy and high‐frequency temporal stability in event simulation compared to prior works.


  • Conditional Product Next Event Estimation for Gaussian Process Implicit Surfaces

    by Song Shi, Kehan Xu, Wojciech Jarosz

    We propose a new next‐event estimation (NEE) technique for Gaussian Process Implicit Surfaces (GPISes). We show that the distribution of surface normals available for sampling at a GPIS hit point collapses from 2D to 1D as the GPIS realizations approach heightfields, causing existing NEE to fail entirely in this limit. We analyze this collapse and develop a new strategy that directly importance samples the resulting 1D arc of valid scattering directions restricted to the spherical cap towards a light source. Our technique enables NEE on heightfield GPISes for the first time and provides substantial variance reduction for highly anisotropic near‐heightfield configurations. We combine our strategy with existing techniques via multiple importance sampling for robust performance across all degrees of anisotropy, and support arbitrary emitter shapes via sphere proxies.


  • Light‐Cone Shell Queries for Scalable Time‐Gated Rendering

    by Jack Cui, Juhyeon Kim, Adithya Pediredla, Wojciech Jarosz

    Monte Carlo time‐gated rendering requires sampling light paths that not only connect a sensor to an emitter, but which also have a total travel time that falls within a narrow interval, a constraint that is difficult to importance sample. We show that this problem has an underlying geometric structure: in the joint space of position and accumulated travel time, the points yielding a time‐valid connection to a given query point form a light‐cone shell. Prior methods sample this shell indirectly. Steady‐state algorithms sample the full space and reject points outside it, giving high variance under tight gates. Ellipsoidal path connections target a single cone surface by intersecting an ellipsoid with scene geometry, coupling cost to scene complexity. Our key observation is that shell membership is cheap to test, needing only accumulated travel time and a Euclidean distance. We therefore store the vertices of traced light subpaths in a 4D spatiotemporal hierarchy and recast time‐gated connection as a range query, using pruning and importance sampling over the shell to select time‐valid vertices without intersecting scene geometry. This decouples the cost of time gating from scene complexity. Within a bidirectional path tracing framework, our method significantly reduces variance over existing approaches on scenes with up to 2.4M triangles.

  • Open Access

    ToF ReSTIR: Time-of-Flight Rendering with Spatio-temporal Reservoir Resampling

    by Juhyeon Kim, Wojciech Jarosz, Adithya Pediredla

    We present a novel spatio-temporal reuse framework for time-resolved light transport, enabling efficient Monte Carlo rendering of time-of-flight (ToF) phenomena such as time-gated imaging and transient light capture. Existing ToF rendering methods are computationally expensive, scale poorly to complex dynamic scenes, and are therefore unsuitable for applications with strict latency constraints. To address this limitation, we draw inspiration from ReSTIR , a reuse-based technique for steady-state real-time rendering, and adapt its core principles to interactive-rate ToF simulation. However, naively applying existing ReSTIR methods to ToF rendering leads to severe inefficiency, as reused paths frequently violate optical path-length constraints and thus contribute little or no signal. We overcome this challenge by introducing a path reuse formulation that explicitly enforces physically valid optical path lengths. The key idea is path-length-aware shift mapping , a geometric transformation based on Newton's method that adjusts reused light paths to satisfy temporal gating constraints, inspired by specular manifold exploration in steady-state caustics rendering. The resulting framework substantially improves the efficiency of ToF rendering across a wide range of scenarios, including complex scenes with glossy or specular materials and dynamic motion. Our method supports both time-gated and transient rendering at interactive frame rates, enabling simulation under practical latency constraints. We demonstrate the effectiveness of our approach through two downstream applications, including shape reconstruction and navigation.


  • Open Access

    Practical Gaussian Process Implicit Surfaces with Sparse Convolutions

    by Kehan Xu, Benedikt Bitterli, Eugene D'EOn, Wojciech Jarosz

    A fundamental challenge in rendering has been the dichotomy between surface and volume models. Gaussian Process Implicit Surfaces (GPISes) recently provided a unified approach for surfaces, volumes, and the spectrum in between. However, this representation remains impractical due to its high computational cost and mathematical complexity. We address these limitations by reformulating GPISes as procedural noise, eliminating expensive linear system solves while maintaining control over spatial correlations. Our method enables efficient sampling of stochastic realizations and supports flexible conditioning of values and derivatives through pathwise updates. To further enable practical rendering, we derive analytic distributions for surface normals, allowing for variance-reduced light transport via next-event estimation and multiple importance sampling. Our framework achieves efficient, high-quality rendering of stochastic surfaces and volumes with significantly simplified implementations on both CPU and GPU, while preserving the generality of the original GPIS representation.


  • Open Access

    Harmonic Caching for Walk on Spheres

    by Zihong Zhou, Eugene D'EOn, Rohan Sawhney, Wojciech Jarosz

    We present a variance reduction technique for Walk on Spheres (WoS) that solves elliptic partial differential equations (PDEs) by combining overlapping harmonic expansions of the solution, each estimated using unbiased Monte Carlo random walks. Our method supports Laplace and screened Poisson equations with Dirichlet, Neumann, and Robin boundary conditions in both 2D and 3D. By adaptively covering the domain with local expansion regions and reconstructing the solution inside each region using an infinite Fourier series of the harmonic function, our method achieves over an order of magnitude lower error than traditional pointwise WoS in equal time. While low-order truncations of the series typically introduce limited bias, we also introduce a stochastic truncation scheme that eliminates this bias in the reconstructed solution. Compared to recently developed caching algorithms for WoS, such as Boundary and Mean Value Caching, our approach yields solutions with lower error and fewer correlation artifacts.


  • Open Access

    A Monte Carlo Rendering Framework for Simulating Optical Heterodyne Detection

    by Juhyeon Kim, Craig Benko, Magnus Wrenninge, Ryusuke Villemin, Zeb Barber, Wojciech Jarosz, Adithya Pediredla

    Optical heterodyne detection (OHD) employs coherent light and optical interference techniques (Fig. 1-(A)) to extract physical parameters, such as velocity or distance, which are encoded in the frequency modulation of the light. With its superior signal-to-noise ratio compared to incoherent detection methods, such as time-of-flight lidar, OHD has become integral to applications requiring high sensitivity, including autonomous navigation, atmospheric sensing, and biomedical velocimetry. However, current simulation tools for OHD focus narrowly on specific applications, relying on domain-specific settings like restricted reflection functions, scene configurations, or single-bounce assumptions, which limit their applicability. In this work, we introduce a flexible and general framework for spectral-domain simulation of OHD. We demonstrate that classical radiometry-based path integral formulation can be adapted and extended to simulate the OHD measurements in the spectral domain. This enables us to leverage the rich modeling and sampling capabilities of existing Monte Carlo path tracing techniques. Our formulation shares structural similarities with transient rendering but operates in the spectral domain and accounts for the Doppler effect (Fig. 1-(B)). While simulators for the Doppler effect in incoherent (intensity) detection methods exist, they are largely not suitable to simulate OHD. We use a microsurface interpretation to show that these two Doppler imaging techniques capture different physical quantities and thus need different simulation frameworks. We validate the correctness and predictive power of our simulation framework by qualitatively comparing the simulations with real-world captured data for three different OHD applications—FMCW lidar, blood flow velocimetry, and wind Doppler lidar (Fig. 1-(C)).


  • A wave‐optics BSDF for correlated scatterers

    by Ruomai Yang, Juhyeon Kim, Adithya Pediredla, Wojciech Jarosz

    We present a wave‐optics‐based BSDF for simulating the corona effect observed when viewing strong light sources through materials such as certain fabrics or glass surfaces with condensation. These visual phenomena arise from the interference of diffraction patterns caused by correlated, disordered arrangements of droplets or pores. Our method leverages the pair correlation function (PCF) to decouple the spatial relationships between scatterers from the diffraction behavior of individual scatterers. This two‐level decomposition allows us to derive a physically based BSDF that provides explicit control over both scatterer shape and spatial correlation. We also introduce a practical importance sampling strategy for integrating our BSDF within a Monte Carlo renderer. Our simulation results and real‐world comparisons demonstrate that the method can reliably reproduce the characteristics of the corona effects in various real‐world diffractive materials.

  • Open Access

    VoD-3DGS: View-opacity-Dependent 3D Gaussian Splatting

    by Mateusz Nowak, Wojciech Jarosz, Peter Chin

    Reconstructing a 3D scene from images is challenging due to the different ways light interacts with surfaces depending on the viewer's position and the surface's material. In classical computer graphics, materials can be classified as diffuse or specular, interacting with light differently. The standard 3D Gaussian Splatting model struggles to represent view-dependent content, since it cannot differentiate an object within the scene from the light interacting with its specular surfaces, which produce highlights or reflections. In this paper, we propose to extend the 3D Gaussian Splatting model by introducing an additional symmetric matrix to enhance the opacity representation of each 3D Gaussian. This improvement allows certain Gaussians to be suppressed based on the viewer's perspective, resulting in a more accurate representation of view-dependent reflections and specular highlights without compromising the scene's integrity. By allowing the opacity to be view dependent, our enhanced model achieves state-of-the-art performance on Mip-Nerf, Tanks&Temples, Deep Blending, and Nerf-Synthetic datasets without a significant loss in rendering speed, achieving >60FPS, and only incurring a minimal increase in memory used.