Neural Product Importance Sampling via Warp Composition

• URL: http://arxiv.org/abs/2409.18974v2
• Date: Sun, 6 Oct 2024 17:40:40 GMT
• Title: Neural Product Importance Sampling via Warp Composition
• Authors: Joey Litalien, Miloš Hašan, Fujun Luan, Krishna Mullia, Iliyan Georgiev,
• Abstract summary: 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.
• Score: 9.846719854600709
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Achieving high efficiency in modern photorealistic rendering hinges on using Monte Carlo sampling distributions that closely approximate the illumination integral estimated for every pixel. Samples are typically generated from a set of simple distributions, each targeting a different factor in the integrand, which are combined via multiple importance sampling. The resulting mixture distribution can be far from the actual product of all factors, leading to sub-optimal variance even for direct-illumination estimation. We present a learning-based method that uses normalizing flows to efficiently importance sample illumination product integrals, e.g., the product of environment lighting and material terms. Our sampler composes a flow head warp with an emitter tail warp. The small conditional head warp is represented by a neural spline flow, while the large unconditional tail is discretized per environment map and its evaluation is instant. If the conditioning is low-dimensional, the head warp can be also discretized to achieve even better performance. We demonstrate variance reduction over prior methods on a range of applications comprising complex geometry, materials and illumination.

Related papers

• TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering [38.74244725059936]
  Inverse rendering aims to recover scene geometry, material properties, and lighting from multi-view images. Given the complexity of light-surface interactions, importance sampling is essential for the evaluation of the rendering equation. Existing inverse rendering methods typically use pre-defined non-learnable importance samplers in prior manually. We propose the concept of learning a spatially and directionally aware importance sampler for the rendering equation to accurately and flexibly capture the unconstrained complexity of a typical scene.
  arXiv  Detail & Related papers  (2025-03-24T04:09:46Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional general score-mismatched diffusion samplers. We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions. This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AI [29.13807697733638]
  We build on the remarkable achievements in generative sampling of natural images. We propose an innovative challenge, potentially overly ambitious, which involves generating samples that resemble images. The statistical challenge lies in the small sample size, sometimes consisting of a few hundred subjects.
  arXiv  Detail & Related papers  (2024-04-10T22:35:06Z)
• SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation [65.99344783327054]
  We present a novel approach for digitizing real-world objects by estimating their geometry, material properties, and lighting. Our method incorporates into Radiance Neural Field (NeRF) pipelines the split sum approximation used with image-based lighting for real-time physical-based rendering. Our method is capable of attaining state-of-the-art relighting quality after only $sim1$ hour of training in a single NVIDIA A100 GPU.
  arXiv  Detail & Related papers  (2023-11-28T10:36:36Z)
• NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering [23.482941494283978]
  This paper presents a method, namely NeuS-PIR, for recovering relightable neural surfaces from multi-view images or video. Unlike methods based on NeRF and discrete meshes, our method utilizes implicit neural surface representation to reconstruct high-quality geometry. Our method enables advanced applications such as relighting, which can be seamlessly integrated with modern graphics engines.
  arXiv  Detail & Related papers  (2023-06-13T09:02:57Z)
• Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion [85.54515118077825]
  This paper proposes a linear diffusion model (LinDiff) based on an ordinary differential equation to simultaneously reach fast inference and high sample quality. To reduce computational complexity, LinDiff employs a patch-based processing approach that partitions the input signal into small patches. Our model can synthesize speech of a quality comparable to that of autoregressive models with faster synthesis speed.
  arXiv  Detail & Related papers  (2023-06-09T07:02:43Z)
• Unsupervised Learning of Sampling Distributions for Particle Filters [80.6716888175925]
  We put forward four methods for learning sampling distributions from observed measurements. Experiments demonstrate that learned sampling distributions exhibit better performance than designed, minimum-degeneracy sampling distributions.
  arXiv  Detail & Related papers  (2023-02-02T15:50:21Z)
• Sensing Cox Processes via Posterior Sampling and Positive Bases [56.82162768921196]
  We study adaptive sensing of point processes, a widely used model from spatial statistics. We model the intensity function as a sample from a truncated Gaussian process, represented in a specially constructed positive basis. Our adaptive sensing algorithms use Langevin dynamics and are based on posterior sampling (textscCox-Thompson) and top-two posterior sampling (textscTop2) principles.
  arXiv  Detail & Related papers  (2021-10-21T14:47:06Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)
• Learning to Importance Sample in Primary Sample Space [22.98252856114423]
  We propose a novel importance sampling technique that uses a neural network to learn how to sample from a desired density represented by a set of samples. We show that our approach leads to effective variance reduction in several practical scenarios.
  arXiv  Detail & Related papers  (2018-08-23T16:55:53Z)

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.