Physically Based Neural Bidirectional Reflectance Distribution Function

• URL: http://arxiv.org/abs/2411.02347v1
• Date: Mon, 04 Nov 2024 18:17:44 GMT
• Title: Physically Based Neural Bidirectional Reflectance Distribution Function
• Authors: Chenliang Zhou, Alejandro Sztrajman, Gilles Rainer, Fangcheng Zhong, Fazilet Gokbudak, Zhilin Guo, Weihao Xia, Rafal Mantiuk, Cengiz Oztireli,
• Abstract summary: We introduce the physically based neural bidirectional reflectance distribution function (PBNBRDF) Our model accurately reconstructs real-world materials while uniquely enforcing physical properties for realistic BRDFs.
• Score: 40.726751711127946
• License:
• Abstract: We introduce the physically based neural bidirectional reflectance distribution function (PBNBRDF), a novel, continuous representation for material appearance based on neural fields. Our model accurately reconstructs real-world materials while uniquely enforcing physical properties for realistic BRDFs, specifically Helmholtz reciprocity via reparametrization and energy passivity via efficient analytical integration. We conduct a systematic analysis demonstrating the benefits of adhering to these physical laws on the visual quality of reconstructed materials. Additionally, we enhance the color accuracy of neural BRDFs by introducing chromaticity enforcement supervising the norms of RGB channels. Through both qualitative and quantitative experiments on multiple databases of measured real-world BRDFs, we show that adhering to these physical constraints enables neural fields to more faithfully and stably represent the original data and achieve higher rendering quality.

Related papers

• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields [56.69755544814834]
  We present evidence suggesting that depthwise convolutional kernels are effectively replicating the biological receptive fields observed in the mammalian retina. We propose a scheme that draws inspiration from the biological receptive fields.
  arXiv  Detail & Related papers  (2024-01-18T18:06:22Z)
• Anisotropic Neural Representation Learning for High-Quality Neural Rendering [0.0]
  We propose an anisotropic neural representation learning method that utilizes learnable view-dependent features to improve scene representation and reconstruction. Our method is flexiable and can be plugged into NeRF-based frameworks.
  arXiv  Detail & Related papers  (2023-11-30T07:29:30Z)
• Real-Time Neural BRDF with Spherically Distributed Primitives [35.09149879060455]
  We propose a novel neural BRDF offering highly versatile material representation, yet with very-light memory and neural computation consumption. Results show that our system achieves real-time rendering with a wide variety of appearances.
  arXiv  Detail & Related papers  (2023-10-12T13:46:36Z)
• Physics-Driven Turbulence Image Restoration with Stochastic Refinement [80.79900297089176]
  Image distortion by atmospheric turbulence is a critical problem in long-range optical imaging systems. Fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions. This paper proposes the Physics-integrated Restoration Network (PiRN) to help the network to disentangle theity from the degradation and the underlying image.
  arXiv  Detail & Related papers  (2023-07-20T05:49:21Z)
• Neural-PBIR Reconstruction of Shape, Material, and Illumination [26.628189591572074]
  We introduce an accurate and highly efficient object reconstruction pipeline combining neural based object reconstruction and physics-based inverse rendering (PBIR) Our pipeline firstly leverages a neural SDF based shape reconstruction to produce high-quality but potentially imperfect object shape. In the last stage, by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination.
  arXiv  Detail & Related papers  (2023-04-26T11:02:04Z)
• Neural Implicit Representations for Physical Parameter Inference from a Single Video [49.766574469284485]
  We propose to combine neural implicit representations for appearance modeling with neural ordinary differential equations (ODEs) for modelling physical phenomena. Our proposed model combines several unique advantages: (i) Contrary to existing approaches that require large training datasets, we are able to identify physical parameters from only a single video. The use of neural implicit representations enables the processing of high-resolution videos and the synthesis of photo-realistic images.
  arXiv  Detail & Related papers  (2022-04-29T11:55:35Z)
• Neural BRDF Representation and Importance Sampling [79.84316447473873]
  We present a compact neural network-based representation of reflectance BRDF data. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real-world datasets.
  arXiv  Detail & Related papers  (2021-02-11T12:00:24Z)
• Invertible Neural BRDF for Object Inverse Rendering [27.86441556552318]
  We introduce a novel neural network-based BRDF model and a Bayesian framework for object inverse rendering. We experimentally validate the accuracy of the invertible neural BRDF model on a large number of measured data. Results show new ways in which deep neural networks can help solve challenging inverse problems.
  arXiv  Detail & Related papers  (2020-08-10T11:27:01Z)

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.