PureLight: Learning Complex Luminaires with Light Tracing

• URL: http://arxiv.org/abs/2606.04319v1
• Date: Wed, 03 Jun 2026 00:48:27 GMT
• Title: PureLight: Learning Complex Luminaires with Light Tracing
• Abstract summary: We use light tracing to construct paths from emitters to the exit surfaces.<n>We distill the learned appearance into a lightweight computation that directly estimates radiance on the exit surfaces.
• Score: 13.516598146561845
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a neural formulation for estimating the appearance of complex luminaires. We focus on challenging luminaires with complex light transport (e.g., small emitters enclosed by multiple specular layers) that are difficult for (bidirectional) path tracing. To this end, we use light tracing to construct paths from emitters to the exit surfaces and formulate appearance estimation as a distribution learning problem. Specifically, we model the probability density function (pdf) of outgoing radiance on the exit surfaces using a large normalizing flow network, and recover the outgoing radiance as the product of the estimated pdf and flux. To enable efficient inference, we distill the learned appearance into a lightweight MLP that directly estimates radiance on the exit surfaces. We additionally train a sampling network for effective direct illumination computation from the luminaire, and a blending network to composite the luminaire into the scene. Our formulation makes it feasible to render challenging luminaires using low sample counts in arbitrary scenes.

Related papers

• AEGIR: Modeling Area Emitters for Indoor Inverse Rendering using Gaussian Splatting [2.333246928962179]
  Inverse rendering requires separating illumination from surface materials.<n>Existing relightable methods approximate scene lighting using discrete point lights, global environment maps, or implicit representations.<n>We present AEGIR, a framework that explicitly models local area emitters within a relightable Gaussian Splatting representation.
  arXiv  Detail & Related papers  (2026-06-26T22:34:23Z)
• Real-time Image-based Lighting of Glints [4.180435324231827]
  A challenging scenario involves materials exhibiting a sparkling or glittering appearance, caused by discrete microfacets scattered across their surface.<n>We propose an efficient approximation for image-based lighting of glints, enabling fully dynamic material properties and environment maps.<n>Compared to rendering smooth materials without glints, our approach requires twice as much memory to store the prefiltered environment map.
  arXiv  Detail & Related papers  (2025-07-03T14:38:37Z)
• Neural Product Importance Sampling via Warp Composition [9.846719854600709]
  We present a learning-based method that uses normalizing flows to efficiently importance sample illumination product integrals. We demonstrate variance reduction over prior methods on a range of applications comprising complex geometry, materials and illumination.
  arXiv  Detail & Related papers  (2024-09-12T15:38:21Z)
• GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization [62.13932669494098]
  This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to factorize the scene into material properties, light, and geometry. We compute the normal of each 3D Gaussian using the shortest eigenvector, with a directional masking scheme forcing accurate normal estimation without external supervision. We adopt an efficient voxel-based indirect illumination tracing scheme that stores direction-aware outgoing radiance in each 3D Gaussian to disentangle secondary illumination for approximating multi-bounce light transport.
  arXiv  Detail & Related papers  (2023-12-08T16:05:15Z)
• Adaptive Shells for Efficient Neural Radiance Field Rendering [92.18962730460842]
  We propose a neural radiance formulation that smoothly transitions between- and surface-based rendering. Our approach enables efficient rendering at very high fidelity. We also demonstrate that the extracted envelope enables downstream applications such as animation and simulation.
  arXiv  Detail & Related papers  (2023-11-16T18:58:55Z)
• Neural Free-Viewpoint Relighting for Glossy Indirect Illumination [44.32630651762033]
  We show a hybrid neural-wavelet PRT solution to high-frequency indirect illumination, including glossy reflection, for relighting with changing view. We demonstrate real-time rendering of challenging scenes involving view-dependent reflections and even caustics.
  arXiv  Detail & Related papers  (2023-07-12T17:56:09Z)
• Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation [97.0195314255101]
  Inverse path tracing is expensive to compute, and ambiguities exist between reflection and emission. Our Factorized Inverse Path Tracing (FIPT) addresses these challenges by using a factored light transport formulation. Our algorithm enables accurate material and lighting optimization faster than previous work, and is more effective at resolving ambiguities.
  arXiv  Detail & Related papers  (2023-04-12T07:46:05Z)
• NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination [48.42173911185454]
  Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. We propose an end-to-end inverse rendering pipeline that decomposes materials and illumination from multi-view images.
  arXiv  Detail & Related papers  (2023-03-29T12:05:19Z)
• A Learned Radiance-Field Representation for Complex Luminaires [0.0]
  We reduce the geometric complexity of luminaires by using a simple proxy geometry. We encode the visually-complex emitted light field by using a neural radiance field. For rendering, we distill our luminaires' NeRF into a Plenoctree, which we can be easily integrated into traditional rendering systems.
  arXiv  Detail & Related papers  (2022-07-11T16:57:59Z)
• Light Stage Super-Resolution: Continuous High-Frequency Relighting [58.09243542908402]
  We propose a learning-based solution for the "super-resolution" of scans of human faces taken from a light stage. Our method aggregates the captured images corresponding to neighboring lights in the stage, and uses a neural network to synthesize a rendering of the face. Our learned model is able to produce renderings for arbitrary light directions that exhibit realistic shadows and specular highlights.
  arXiv  Detail & Related papers  (2020-10-17T23:40:43Z)
• Deep Photometric Stereo for Non-Lambertian Surfaces [89.05501463107673]
  We introduce a fully convolutional deep network for calibrated photometric stereo, which we call PS-FCN. PS-FCN learns the mapping from reflectance observations to surface normal, and is able to handle surfaces with general and unknown isotropic reflectance. To deal with the uncalibrated scenario where light directions are unknown, we introduce a new convolutional network, named LCNet, to estimate light directions from input images.
  arXiv  Detail & Related papers  (2020-07-26T15:20:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.