pith. machine review for the scientific record. sign in

arxiv: 2605.11536 · v1 · submitted 2026-05-12 · 💻 cs.GR

Recognition: no theorem link

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

Adithya Pediredla, Juhyeon Kim, Wojciech Jarosz

Pith reviewed 2026-05-13 02:16 UTC · model grok-4.3

classification 💻 cs.GR
keywords time-of-flight renderingMonte Carloreservoir resamplingspatio-temporal reusepath shift mappingtime-gated imagingtransient renderingreal-time graphics
0
0 comments X

The pith

Path-length-aware shift mapping lets reservoir resampling render time-of-flight light transport at interactive rates.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes a spatio-temporal reuse method for Monte Carlo time-of-flight rendering by adapting reservoir resampling to enforce optical path-length constraints. Existing reuse approaches break down because reused paths often fall outside the required time gates and contribute no signal. The authors solve this with a geometric adjustment based on Newton's method that transforms paths while keeping them physically valid. If the approach holds, complex scenes with specular surfaces and motion become renderable in real time for both gated imaging and full transient capture, directly supporting latency-sensitive uses such as shape reconstruction.

Core claim

A path reuse formulation that explicitly enforces physically valid optical path lengths via path-length-aware shift mapping, a geometric transformation based on Newton's method, enables efficient unbiased Monte Carlo simulation of time-of-flight phenomena at interactive frame rates even in dynamic scenes with glossy or specular materials.

What carries the argument

path-length-aware shift mapping: a Newton's-method geometric adjustment that transforms reused light paths to satisfy temporal gating constraints while preserving the signal contribution.

If this is right

  • Enables both time-gated and full transient rendering at interactive rates.
  • Scales to scenes with glossy materials and object motion without specialized hardware.
  • Directly supports downstream tasks such as shape reconstruction from time-of-flight data.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same length-enforcement idea could be tested on other time-dependent path-reuse problems such as motion-blur or wave-optics simulation.
  • If the mapping cost stays low, the technique might reduce the sample count needed for production-quality ToF effects in offline pipelines as well.

Load-bearing premise

The Newton's-method shift mapping can reliably and efficiently adjust reused paths to valid lengths without introducing bias or prohibitive cost in complex dynamic scenes.

What would settle it

Rendered frames from a dynamic specular scene either match a high-sample ground-truth reference within statistical noise or diverge visibly when the shift mapping fails to converge on many paths.

Figures

Figures reproduced from arXiv: 2605.11536 by Adithya Pediredla, Juhyeon Kim, Wojciech Jarosz.

Figure 1
Figure 1. Figure 1: We propose a real-time Time-of-Flight (ToF) rendering method inspired by ReSTIR, a state-of-the-art technique for steady-state real-time rendering, [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of proposed path-length-aware reuse strategies. (A) Naive [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: Specular material imposes a 2D constraint, which uniquely deter [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Methods for imposing an additional constraint. (A) A fixed-axis [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Two types of path-length-aware shift mappings are used for different [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: (A) Path length ℓ(𝜉 ) on the plane, forming ellipsoidal iso-value contours. (B) Temporal derivative of path length, d d𝑡 ℓ(𝜉 ), on the plane under three different scenarios: (1) the plane moves upward, (2) p2 moves away, and (3) the plane rotates, each producing distinct iso-value contours. This constraint defines a different manifold from the path-length manifold considered earlier. We visualize examples … view at source ↗
Figure 9
Figure 9. Figure 9: (A) Lin et al. [2022] stores the hit record of the reconnection vertex along with additional information (incident direction 𝜔i and radiance 𝐿i ) to recompute the offset path throughput. (B) We additionally store the next vertex after the reconnection vertex and attach this information to that vertex instead of the original reconnection vertex. The red arrow indicates path-length-aware shift mapping. to ga… view at source ↗
Figure 10
Figure 10. Figure 10: Comparison of the Cornell-Box scene with various objects and materials under an equal time budget. All images are rendered at a resolution of 1024 × 1024, with the maximum path depth set to 6. only occur along ellipsoidal loci that satisfy the path-length con￾straint. In contrast, our proposed path-length-aware shift mapping produces the best results across different scenarios, as it ensures that reused p… view at source ↗
Figure 11
Figure 11. Figure 11: (A) MAPE comparison under different time-gate widths within a [PITH_FULL_IMAGE:figures/full_fig_p010_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Comparison of gauge directions using fixed horizontal and vertical [PITH_FULL_IMAGE:figures/full_fig_p010_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: We implement ellipsoidal path connection [Pediredla et al [PITH_FULL_IMAGE:figures/full_fig_p011_13.png] view at source ↗
Figure 15
Figure 15. Figure 15: Comparison between ellipsoidal path connection, direct connection, [PITH_FULL_IMAGE:figures/full_fig_p012_15.png] view at source ↗
Figure 14
Figure 14. Figure 14: Results of path-length shrink mapping using a rough time gate. (A) [PITH_FULL_IMAGE:figures/full_fig_p012_14.png] view at source ↗
Figure 16
Figure 16. Figure 16: Four scenarios demonstrating the proposed path temporal reuse. (A) Streamed transient rendering in a static [PITH_FULL_IMAGE:figures/full_fig_p013_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Comparison of path reuse in transient histogram rendering with [PITH_FULL_IMAGE:figures/full_fig_p014_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Comparison of our method with progressive KDE [Jarabo et al [PITH_FULL_IMAGE:figures/full_fig_p014_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: Doppler frequency shift rendering under different frequencies. The [PITH_FULL_IMAGE:figures/full_fig_p015_19.png] view at source ↗
Figure 20
Figure 20. Figure 20: Simulation of NLOS imaging with temporal focusing [Pediredla [PITH_FULL_IMAGE:figures/full_fig_p015_20.png] view at source ↗
Figure 21
Figure 21. Figure 21: We simulate NLOS navigation [Young et al [PITH_FULL_IMAGE:figures/full_fig_p016_21.png] view at source ↗
read the original abstract

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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper presents ToF ReSTIR, a spatio-temporal reservoir resampling framework for Monte Carlo rendering of time-resolved light transport. It adapts ReSTIR to time-of-flight (ToF) phenomena by introducing path-length-aware shift mapping based on Newton's method to enforce optical path-length constraints on reused paths, addressing the inefficiency of naive reuse under temporal gating. The method is claimed to support both time-gated and transient rendering at interactive rates in complex dynamic scenes with glossy or specular materials, with demonstrations in shape reconstruction and navigation applications.

Significance. If the central efficiency claims hold with unbiased estimators and reliable convergence, the work would represent a meaningful advance in real-time ToF simulation, extending reuse-based techniques to time-resolved domains and enabling practical latency-constrained applications in graphics and vision. The combination of ReSTIR-style resampling with geometric adjustments inspired by specular manifold exploration is a natural and potentially high-impact direction.

major comments (2)
  1. [Path-length-aware shift mapping section] The efficiency and unbiasedness claims rest on the path-length-aware shift mapping (described in the core technical section following the ReSTIR adaptation). The manuscript must provide a concrete analysis or proof that Newton's method iterations converge reliably across the tested scenes and that any non-convergent or rejected paths are handled with proper importance weighting or MIS correction; otherwise the estimator risks bias when the nonlinear path-length constraint has multiple roots or none, as can occur in dynamic specular geometry.
  2. [Results and evaluation section] No quantitative results, error bounds, or bias analysis appear in the provided text to support the central claim of substantial efficiency gains and interactive rates. The manuscript should include tables or figures reporting per-frame timings, sample counts, and error metrics (e.g., MSE vs. reference) across the claimed scenarios, including failure cases for the shift mapping.
minor comments (1)
  1. [Abstract and Introduction] The abstract and introduction would benefit from a brief statement of the precise mathematical formulation of the shift mapping (e.g., the objective function minimized by Newton's method) to allow readers to assess the geometric adjustment without immediately consulting the full methods.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments and the recommendation for major revision. We address each point below and will incorporate the suggested improvements into the revised manuscript.

read point-by-point responses
  1. Referee: [Path-length-aware shift mapping section] The efficiency and unbiasedness claims rest on the path-length-aware shift mapping (described in the core technical section following the ReSTIR adaptation). The manuscript must provide a concrete analysis or proof that Newton's method iterations converge reliably across the tested scenes and that any non-convergent or rejected paths are handled with proper importance weighting or MIS correction; otherwise the estimator risks bias when the nonlinear path-length constraint has multiple roots or none, as can occur in dynamic specular geometry.

    Authors: We appreciate the referee's emphasis on rigorously establishing unbiasedness. The path-length-aware shift mapping employs Newton's method to iteratively solve for the vertex adjustment that satisfies the optical path-length constraint imposed by temporal gating, following the geometric approach of specular manifold exploration. In the manuscript we describe the iteration and note rapid convergence in practice. To strengthen the submission we will add a new subsection with empirical convergence data (average iterations, success rates per scene type, and histograms) across all tested dynamic scenes. Non-convergent paths are rejected by setting their contribution to zero; the rejection probability is folded into the resampling weight via the standard ReSTIR MIS correction, preserving unbiasedness. We will also explicitly discuss the handling of multiple roots by selecting the solution whose path length lies inside the active gating interval. revision: yes

  2. Referee: [Results and evaluation section] No quantitative results, error bounds, or bias analysis appear in the provided text to support the central claim of substantial efficiency gains and interactive rates. The manuscript should include tables or figures reporting per-frame timings, sample counts, and error metrics (e.g., MSE vs. reference) across the claimed scenarios, including failure cases for the shift mapping.

    Authors: We agree that the results section requires more quantitative support. The current manuscript contains timing measurements and visual comparisons, yet we acknowledge that tabulated MSE values, per-frame statistics, and explicit failure-case analysis were insufficiently detailed. In the revision we will expand the evaluation with (i) a table of per-frame timings and effective sample counts for both time-gated and transient modes, (ii) MSE plots against path-traced references for representative scenes, and (iii) a dedicated figure and accompanying text quantifying shift-mapping failure rates together with the resulting error contribution. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation introduces independent geometric adjustment

full rationale

The paper's core contribution is a new path-length-aware shift mapping (Newton's method) that enforces optical path-length constraints when adapting ReSTIR to ToF rendering. This step is presented as a novel geometric transformation inspired by (but not defined by) prior specular manifold exploration work. No equations reduce the claimed efficiency gains or the shift-mapping procedure to fitted parameters, self-definitions, or load-bearing self-citations. The method is self-contained against external benchmarks such as standard ReSTIR and manifold exploration; the derivation chain does not collapse by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no explicit free parameters, axioms, or invented entities; the shift mapping implicitly relies on iterative numerical solving whose convergence parameters are unspecified.

pith-pipeline@v0.9.0 · 5549 in / 1111 out tokens · 52097 ms · 2026-05-13T02:16:39.937156+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

52 extracted references · 52 canonical work pages

  1. [1]

    Marco Ament, Christoph Bergmann, and Daniel Weiskopf

    Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo.IEEE Transactions on Pattern Analysis and Machine Intelligence(2016). Marco Ament, Christoph Bergmann, and Daniel Weiskopf

  2. [2]

    doi:10/gbf323 Ian M Baker, Stuart S Duncan, and Jeremy W Copley

    Refractive Radiative Transfer Equation.ACM Transactions on Graphics33, 2 (April 2014), 17:1–17:22. doi:10/gbf323 Ian M Baker, Stuart S Duncan, and Jeremy W Copley

  3. [3]

    doi:10/gg8xc7 Mauro Buttafava, Jessica Zeman, Alberto Tosi, Kevin Eliceiri, and Andreas Velten

    Spatiotemporal Reservoir Resampling for Real-Time Ray Tracing with Dynamic Direct Lighting.ACM Transactions on Graphics (Proceedings of SIGGRAPH) 39, 4 (July 2020). doi:10/gg8xc7 Mauro Buttafava, Jessica Zeman, Alberto Tosi, Kevin Eliceiri, and Andreas Velten

  4. [4]

    Optics Express23, 16 (2015)

    Non-Line-of-Sight Imaging Using a Time-Gated Single Photon Avalanche Diode. Optics Express23, 16 (2015). doi:10/gfz5k4 Lucrezia Cester, Ashley Lyons, Maria Chiara Braidotti, and Daniele Faccio

  5. [5]

    Time- of-Flight Imaging at 10 ps Resolution with an ICCD Camera.Sensors19, 1 (2019),

  6. [6]

    1982), 653–656

    A General Purpose Unequal Probability Sampling Plan.Biometrika 69, 3 (Dec. 1982), 653–656. doi:10/fd87zs Zhimin Fan, Jie Guo, Yiming Wang, Tianyu Xiao, Hao Zhang, Chenxi Zhou, Zhenyu Chen, Pengpei Hong, Yanwen Guo, and Ling-Qi Yan

  7. [7]

    ACM Transactions on Graphics (TOG)43, 4 (2024), 1–13

    Specular Polynomials. ACM Transactions on Graphics (TOG)43, 4 (2024), 1–13. Zhimin Fan, Pengpei Hong, Jie Guo, Changqing Zou, Yanwen Guo, and Ling-Qi Yan

  8. [8]

    Genevieve Gariepy, Nikola Krstajić, Robert Henderson, Chunyong Li, Robert R Thom- son, Gerald S Buller, Barmak Heshmat, Ramesh Raskar, Jonathan Leach, and Daniele Faccio

    Manifold path guiding for importance sampling specular chains.ACM Transactions on Graphics (TOG)42, 6 (2023), 1–14. Genevieve Gariepy, Nikola Krstajić, Robert Henderson, Chunyong Li, Robert R Thom- son, Gerald S Buller, Barmak Heshmat, Ramesh Raskar, Jonathan Leach, and Daniele Faccio

  9. [9]

    Ioannis Gkioulekas, Anat Levin, Frédo Durand, and Todd Zickler

    Single-Photon Sensitive Light-in-Fight Imaging.Nature Communica- tions6 (2015). Ioannis Gkioulekas, Anat Levin, Frédo Durand, and Todd Zickler

  10. [10]

    doi:10/f7mzkt Yoav Grauer and Ezri Sonn

    Micron-Scale Light Transport Decomposition Using Interferometry.ACM Transactions on Graphics (Proceedings of SIGGRAPH)34, 4 (2015). doi:10/f7mzkt Yoav Grauer and Ezri Sonn

  11. [11]

    InVideo Surveillance and Transportation Imaging Applications 2015, Vol

    Active gated imaging for automotive safety applica- tions. InVideo Surveillance and Transportation Imaging Applications 2015, Vol

  12. [12]

    doi:10/gfzv83 Trevor Hedstrom, Markus Kettunen, Daqi Lin, Chris Wyman, and Tzu-Mao Li

    Improved Half Vector Space Light Transport.Computer Graphics Forum (Proceedings of the Euro- graphics Symposium on Rendering)34, 4 (July 2015), 65–74. doi:10/gfzv83 Trevor Hedstrom, Markus Kettunen, Daqi Lin, Chris Wyman, and Tzu-Mao Li

  13. [13]

    Felix Heide, Matthias B

    ReSTIR BDPT: Bidirectional ReSTIR Path Tracing with Caustics.ACM Transactions on Graphics(2025). Felix Heide, Matthias B. Hullin, James Gregson, and Wolfgang Heidrich

  14. [14]

    Low- Budget Transient Imaging Using Photonic Mixer Devices.ACM Transactions on Graphics (Proceedings of SIGGRAPH)32, 4 (July 2013), 45:1–45:10. doi:10/gbdg7s Robert K Henderson, Nick Johnston, Francescopaolo Mattioli Della Rocca, Haochang Chen, David Day-Uei Li, Graham Hungerford, Richard Hirsch, David Mcloskey, Philip Yip, and David JS Birch

  15. [15]

    Pengpei Hong, Meng Duan, Beibei Wang, Cem Yuksel, Tizian Zeltner, and Daqi Lin

    A 192x128 time correlated SPAD image sensor in 40-nm CMOS technology.IEEE Journal of Solid-State Circuits54, 7 (2019), 1907–1916. Pengpei Hong, Meng Duan, Beibei Wang, Cem Yuksel, Tizian Zeltner, and Daqi Lin

  16. [16]

    InProceedings of the SIGGRAPH Asia 2025 Conference Papers

    Sample Space Partitioning and Spatiotemporal Resampling for Specular Manifold Sampling. InProceedings of the SIGGRAPH Asia 2025 Conference Papers. 1–10. Binh-Son Hua, Adrien Gruson, Victor Petitjean, Matthias Zwicker, Derek Nowrouzezahrai, Elmar Eisemann, and Toshiya Hachisuka

  17. [17]

    doi:10/ggd8m5 Julian Iseringhausen and Matthias B

    A Survey on Gradient-Domain Rendering.Computer Graphics Forum (Proceedings of Eurographics State of the Art Reports)38, 2 (2019), 455–472. doi:10/ggd8m5 Julian Iseringhausen and Matthias B. Hullin

  18. [18]

    2020), 8:1–8:14

    Non-Line-of-Sight Reconstruction Using Efficient Transient Rendering.ACM Transactions on Graphics39, 1 (Jan. 2020), 8:1–8:14. doi:10/gspq3m ACM Trans. Graph., Vol. 45, No. 4, Article

  19. [19]

    ACM Transactions on Graphics (Proceedings of SIGGRAPH)31, 4 (July 2012), 58:1– 58:13

    Manifold Exploration: A Markov Chain Monte Carlo Technique for Rendering Scenes with Difficult Specular Transport. ACM Transactions on Graphics (Proceedings of SIGGRAPH)31, 4 (July 2012), 58:1– 58:13. doi:10/gfzq4p Wenzel Alban Jakob. 2013.Light Transport on Path-Space Manifolds. Ph. D. Dissertation. Cornell University. Adrian Jarabo. 2012.Femto-Photograp...

  20. [20]

    2014), 177:1–177:10

    A Framework for Transient Rendering.ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)33, 6 (Nov. 2014), 177:1–177:10. doi:10/ gfznb8 Adrian Jarabo, Belen Masia, Julio Marco, and Diego Gutierrez

  21. [21]

    doi:10/gfz5mh Wojciech Jarosz, Derek Nowrouzezahrai, Robert Thomas, Peter-Pike Sloan, and Matthias Zwicker

    Recent Advances in Transient Imaging: A Computer Graphics and Vision Perspective.Visual Informatics 1, 1 (2017), 65–79. doi:10/gfz5mh Wojciech Jarosz, Derek Nowrouzezahrai, Robert Thomas, Peter-Pike Sloan, and Matthias Zwicker

  22. [22]

    2011), 181:1–181:12

    Progressive Photon Beams.ACM Transactions on Graphics (Proceed- ings of SIGGRAPH Asia)30, 6 (Dec. 2011), 181:1–181:12. doi:10/fn5xzj Achuta Kadambi, Jamie Schiel, and Ramesh Raskar

  23. [23]

    ACM Transactions on Graphics (Proceedings of SIGGRAPH)33, 4 (July 2014), 102:1– 102:13

    The Natural- Constraint Representation of the Path Space for Efficient Light Transport Simulation. ACM Transactions on Graphics (Proceedings of SIGGRAPH)33, 4 (July 2014), 102:1– 102:13. doi:10/f6cz85 Markus Kettunen, Marco Manzi, Miika Aittala, Jaakko Lehtinen, Frédo Durand, and Matthias Zwicker

  24. [24]

    Juhyeon Kim, Craig Benko, Magnus Wrenninge, Ryusuke Villemin, Zeb Barber, Woj- ciech Jarosz, and Adithya Pediredla

    Gradient-domain path tracing.ACM Transactions on Graphics (TOG)34, 4 (2015), 1–13. Juhyeon Kim, Craig Benko, Magnus Wrenninge, Ryusuke Villemin, Zeb Barber, Woj- ciech Jarosz, and Adithya Pediredla

  25. [25]

    Juhyeon Kim, Wojciech Jarosz, Ioannis Gkioulekas, and Adithya Pediredla

    A Monte Carlo Rendering Framework for Simulating Optical Heterodyne Detection.ACM Transactions on Graphics (TOG)44, 4 (2025), 1–19. Juhyeon Kim, Wojciech Jarosz, Ioannis Gkioulekas, and Adithya Pediredla

  26. [26]

    Ahmed Kirmani, Tyler Hutchison, James Davis, and Ramesh Raskar

    Doppler Time-of-Flight Rendering.ACM Transactions on Graphics (TOG)42, 6 (2023), 1–18. Ahmed Kirmani, Tyler Hutchison, James Davis, and Ramesh Raskar

  27. [27]

    doi:10/dsk2dt Jonathan Klein, Christoph Peters, Jaime Martín, Martin Laurenzis, and Matthias B Hullin

    Looking around the Corner Using Ultrafast Transient Imaging.International Journal of Computer Vision (IJCV)95, 1 (2011). doi:10/dsk2dt Jonathan Klein, Christoph Peters, Jaime Martín, Martin Laurenzis, and Matthias B Hullin

  28. [28]

    Scientific Reports6 (2016)

    Tracking Objects Outside the Line of Sight Using 2D Intensity Images. Scientific Reports6 (2016). doi:10/f82649 Martin Laurenzis and Andreas Velten

  29. [29]

    doi:10/gfz5mr Jaakko Lehtinen, Tero Karras, Samuli Laine, Miika Aittala, Frédo Durand, and Timo Aila

    Nonline-of-Sight Laser Gated Viewing of Scattered Photons.Optical Engineering53, 2 (2014). doi:10/gfz5mr Jaakko Lehtinen, Tero Karras, Samuli Laine, Miika Aittala, Frédo Durand, and Timo Aila

  30. [30]

    doi:10/gbdghd He Li, Beibei Wang, Changhe Tu, Kun Xu, Nicolas Holzschuch, and Ling-Qi Yan

    Gradient-Domain Metropolis Light Transport.ACM Transactions on Graphics (Proceedings of SIGGRAPH)32, 4 (July 2013), 95:1–95:12. doi:10/gbdghd He Li, Beibei Wang, Changhe Tu, Kun Xu, Nicolas Holzschuch, and Ling-Qi Yan

  31. [31]

    doi:10/gqjn7b Daqi Lin, Chris Wyman, and Cem Yuksel

    Generalized Resampled Importance Sampling: Foundations of ReSTIR.ACM Transactions on Graphics (Proceedings of SIGGRAPH)41, 4 (July 2022), 75:1–75:23. doi:10/gqjn7b Daqi Lin, Chris Wyman, and Cem Yuksel

  32. [32]

    Fast Volume Rendering with Spa- tiotemporal Reservoir Resampling.ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)40, 6 (Dec. 2021). doi:10/grrjd6 Jeffrey Liu, Daqi Lin, Markus Kettunen, Chris Wyman, and Ravi Ramamoorthi

  33. [33]

    doi:10.1111/cgf.14584 Julio Marco

    Temporally Sliced Photon Primi- tives for Time-of-Flight Rendering.Computer Graphics Forum (Proceedings of the Eurographics Symposium on Rendering)41, 4 (2022). doi:10.1111/cgf.14584 Julio Marco. 2013.Transient Light Transport in Participating Media. Ph. D. Dissertation. Universidad de Zaragoza. Julio Marco, Ibón Guillén, Wojciech Jarosz, Diego Gutierrez,...

  34. [34]

    doi:10/gfvr9w Matthew O’Toole, Felix Heide, Lei Xiao, Matthias B

    Progressive Transient Photon Beams.Computer Graphics Forum38, 1 (March 2019). doi:10/gfvr9w Matthew O’Toole, Felix Heide, Lei Xiao, Matthias B. Hullin, Wolfgang Heidrich, and Kiriakos N. Kutulakos

  35. [35]

    doi:10/gfz5m2 Yaobin Ouyang, Shiqiu Liu, Markus Kettunen, Matt Pharr, and Jacopo Pantaleoni

    Temporal Frequency Probing for 5D Transient Analysis of Global Light Transport.ACM Transactions on Graphics (Proceedings of SIGGRAPH) 33, 4 (2014), 87:1–87:11. doi:10/gfz5m2 Yaobin Ouyang, Shiqiu Liu, Markus Kettunen, Matt Pharr, and Jacopo Pantaleoni

  36. [36]

    doi:10/gqwmdx Adithya Pediredla, Akshat Dave, and Ashok Veeraraghavan

    ReSTIR GI: Path Resampling for Real-Time Path Tracing.Computer Graphics Forum 40, 8 (2021), 17–29. doi:10/gqwmdx Adithya Pediredla, Akshat Dave, and Ashok Veeraraghavan. 2019a. SNLOS: Non-line- of-sight Scanning through Temporal Focusing. InIEEE International Conference on Computational Photography (ICCP). 1–13. doi:10/gspq34 Adithya Pediredla, Ashok Veer...

  37. [37]

    doi:10/f7wqfq Diego Royo, Jorge García, Adolfo Muñoz, and Adrian Jarabo

    Solving Trigonometric Moment Problems for Fast Transient Imaging.ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)34, 6 (2015). doi:10/f7wqfq Diego Royo, Jorge García, Adolfo Muñoz, and Adrian Jarabo

  38. [38]

    2022), 84–92

    Non-Line-of-Sight Transient Rendering.Computers & Graphics107 (Oct. 2022), 84–92. doi:10/gspq3r Diego Royo, Jorge Garcia-Pueyo, Miguel Crespo, Óscar Pueyo-Ciutad, Guillermo En- guita, and Diego Bielsa

  39. [39]

    arXiv:2510.25660 [cs.GR] https://arxiv.org/abs/2510.25660 Rohan Sawhney, Daqi Lin, Markus Kettunen, Benedikt Bitterli, Ravi Ramamoorthi, Chris Wyman, and Matt Pharr

  40. [40]

    arXiv:2211.00166 [cs] doi:10.48550/arXiv.2211.00166 Siddharth Somasundaram, Akshat Dave, Connor Henley, Ashok Veeraraghavan, and Ramesh Raskar

    Decorrelating ReSTIR Samplers via MCMC Mutations. arXiv:2211.00166 [cs] doi:10.48550/arXiv.2211.00166 Siddharth Somasundaram, Akshat Dave, Connor Henley, Ashok Veeraraghavan, and Ramesh Raskar

  41. [41]

    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Role of transients in two-bounce non-line-of-sight imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9192–9201. Justin F. Talbot. 2005.Importance Resampling for Global Illumination. Master’s thesis. Brigham Young University. https://scholarsarchive.byu.edu/etd/663 Justin F. Talbot, David Cline, and Parris Egbert

  42. [42]

    InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition

    The geometry of first-returning photons for non-line-of-sight imaging. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7216–7224. Eric Veach. 1997.Robust Monte Carlo Methods for Light Transport Simulation. Ph. D. Dissertation. Stanford University. Andreas Velten, Thomas Willwacher, Otkrist Gupta, Ashok Veeraraghavan, Moung...

  43. [43]

    Andreas Velten, Di Wu, Adrian Jarabo, Belen Masia, Christopher Barsi, Chinmaya Joshi, Everett Lawson, Moungi Bawendi, Diego Gutierrez, and Ramesh Raskar

    Recovering Three-Dimensional Shape around a Corner Using Ultrafast Time-of-Flight Imaging.Nature Communications3 (2012). Andreas Velten, Di Wu, Adrian Jarabo, Belen Masia, Christopher Barsi, Chinmaya Joshi, Everett Lawson, Moungi Bawendi, Diego Gutierrez, and Ramesh Raskar

  44. [44]

    doi:10/gfxpkt Di Wu, Andreas Velten, Matthew O’Toole, Belen Masia, Amit Agrawal, Qionghai Dai, and Ramesh Raskar

    Femto-Photography: Capturing and Visualizing the Propagation of Light.ACM Transactions on Graphics (Proceedings of SIGGRAPH)32, 4, Article 44 (July 2013), 8 pages. doi:10/gfxpkt Di Wu, Andreas Velten, Matthew O’Toole, Belen Masia, Amit Agrawal, Qionghai Dai, and Ramesh Raskar

  45. [45]

    doi:10/f5v589 Lifan Wu, Guangyan Cai, Ravi Ramamoorthi, and Shuang Zhao

    Decomposing Global Light Transport Using Time of Flight Imaging.International Journal of Computer Vision (IJCV)107 (2014). doi:10/f5v589 Lifan Wu, Guangyan Cai, Ravi Ramamoorthi, and Shuang Zhao

  46. [46]

    Differentiable Time-Gated Rendering.ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)40, 6 (Dec. 2021). doi:10/h2c9 Xiaofeng Xu, Lu Wang, and Beibei Wang

  47. [47]

    Differentiable Transient Rendering.ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)40, 6 (Dec. 2021). doi:10/h2db Aaron Young, Nevindu M Batagoda, Harry Zhang, Akshat Dave, Adithya Pediredla, Dan Negrut, and Ramesh Raskar

  48. [48]

    Tizian Zeltner, Iliyan Georgiev, and Wenzel Jakob

    Principles and features of single-photon avalanche diode arrays.Sensors and Actuators A: Physical140, 1 (2007), 103–112. Tizian Zeltner, Iliyan Georgiev, and Wenzel Jakob

  49. [49]

    doi:10/gg8xc8 Zheng Zeng, Markus Kettunen, Chris Wyman, Lifan Wu, Ravi Ramamoorthi, Ling-Qi Yan, and Daqi Lin

    Specular Manifold Sampling for Rendering High-Frequency Caustics and Glints.ACM Transactions on Graphics (Proceedings of SIGGRAPH)39, 4 (July 2020). doi:10/gg8xc8 Zheng Zeng, Markus Kettunen, Chris Wyman, Lifan Wu, Ravi Ramamoorthi, Ling-Qi Yan, and Daqi Lin

  50. [50]

    InProceedings of the SIGGRAPH Asia 2025 Conference Papers

    ReSTIR PG: Path Guiding with Spatiotemporally Resampled Paths. InProceedings of the SIGGRAPH Asia 2025 Conference Papers. 1–11. Song Zhang, Daqi Lin, Markus Kettunen, Cem Yuksel, and Chris Wyman

  51. [51]

    ACM Trans

    Area ReSTIR: Resampling for Real-Time Defocus and Antialiasing.ACM Transactions on Graphics (TOG)43, 4 (2024), 1–13. ACM Trans. Graph., Vol. 45, No. 4, Article

  52. [52]

    Publication date: July 2026