Hierarchical neural reconstruction for path guiding using hybrid path and photon samples

Zhu, Shilin; Xu, Zexiang; Sun, Tongqing; Кuznetsov, Alexandr; Meyer, Mark; Jensen, Henrik Wann; Su, Hao; Ramamoorthi, Ravi

doi:10.1145/3450626.3459810

Cited by 6 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to Lafortune and Willems [LW95], Müller et al [MGN17] introduce a 5D spatio‐directional tree (SD‐tree) to approximate incident radiance, which does not require expensive fitting and can be used for sampling directly. Zhu et al [ZXS∗21] use a neural network to combine light and camera path samples to reconstruct an SD‐tree for guiding. Bako et al [BMDS19] train a neural network to reconstruct a local radiance field from neighboring samples and use it to guide importance sampling at the first bounce.…”

Section: Background and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Path Guiding with Vertex Triplet Distributions

Schüßler

Hanika

Jung

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

Good importance sampling strategies are decisive for the quality and robustness of photorealistic image synthesis with Monte Carlo integration. Path guiding approaches use transport paths sampled by an existing base sampler to build and refine a guiding distribution. This distribution then guides subsequent paths in regions that are otherwise hard to sample. We observe that all terms in the measurement contribution function sampled during path construction depend on at most three consecutive path vertices. We thus propose to build a 9D guiding distribution over vertex triplets that adapts to the full measurement contribution with a 9D Gaussian mixture model (GMM). For incremental path sampling, we query the model for the last two vertices of a path prefix, resulting in a 3D conditional distribution with which we sample the next vertex along the path. To make this approach scalable, we partition the scene with an octree and learn a local GMM for each leaf separately. In a learning phase, we sample paths using the current guiding distribution and collect triplets of path vertices. We resample these triplets online and keep only a fixed-size subset in reservoirs. After each progression, we obtain new GMMs from triplet samples by an initial hard clustering followed by expectation maximization. Since we model 3D vertex positions, our guiding distribution naturally extends to participating media. In addition, the symmetry in the GMM allows us to query it for paths constructed by a light tracer. Therefore our method can guide both a path tracer and light tracer from a jointly learned guiding distribution. CCS Concepts• Computing methodologies → Ray tracing;

show abstract

Section: Background and Related Workmentioning

confidence: 99%

“…Previous work [VKŠ∗14] therefore learn sampling for path and light tracing separately. The combination of guiding information from path and light tracing has only been achieved previously by using neural networks [ZXS∗21].…”

Section: Overview and Theoretical Backgroundmentioning

confidence: 99%

Path Guiding with Vertex Triplet Distributions

Schüßler

Hanika

Jung

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

Simulation system for collisions and two-way coupling of non-Newtonian fluids and solids

Zhang

Ban

Guo

et al. 2021

Simulation Modelling Practice and Theory

View full text Add to dashboard Cite

Neural Path Sampling for Rendering Pure Specular Light Transport

Yu,

Dong,

Kong

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Multi‐bounce, pure specular light paths produce complex lighting effects, such as caustics and sparkle highlights, which are challenging to render due to their sparse and diverse nature. We introduce a learning‐based method for the efficient rendering of pure specular light transport. The key idea is training a neural network to model the distribution of all specular light paths between pairs of endpoints for one specular object. To achieve this, for each object, our method models the distribution of sparse and diverse specular light paths between two endpoints using smooth 2D maps of ray directions from one endpoint and represents these maps with a 2D convolutional network. We design a training scheme to efficiently sample specular light paths from the scene and train the network. Once trained, our method predicts specular light paths for a given pair of endpoints using the network and employs root‐finding‐based algorithms for rendering the specular light transport. Experimental results demonstrate that our method generates high‐quality results, supports dynamic lighting and moving objects within the scene, and significantly enhances the rendering speed of existing techniques.

show abstract

Hierarchical neural reconstruction for path guiding using hybrid path and photon samples

Cited by 6 publications

References 42 publications

Path Guiding with Vertex Triplet Distributions

Path Guiding with Vertex Triplet Distributions

Simulation system for collisions and two-way coupling of non-Newtonian fluids and solids

Neural Path Sampling for Rendering Pure Specular Light Transport

Contact Info

Product

Resources

About