A Convolutional Neural Deferred Shader for Physics Based Rendering

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: He, Zhuo, Ru, Yingdong, Liu, Qianying, Henderson, Paul, Pugeault, Nicolas
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909973634613248
author He, Zhuo
Ru, Yingdong
Liu, Qianying
Henderson, Paul
Pugeault, Nicolas
author_facet He, Zhuo
Ru, Yingdong
Liu, Qianying
Henderson, Paul
Pugeault, Nicolas
contents Recent advances in neural rendering have achieved impressive results on photorealistic shading and relighting, by using a multilayer perceptron (MLP) as a regression model to learn the rendering equation from a real-world dataset. Such methods show promise for photorealistically relighting real-world objects, which is difficult to classical rendering, as there is no easy-obtained material ground truth. However, significant challenges still remain the dense connections in MLPs result in a large number of parameters, which requires high computation resources, complicating the training, and reducing performance during rendering. Data driven approaches require large amounts of training data for generalization; unbalanced data might bias the model to ignore the unusual illumination conditions, e.g. dark scenes. This paper introduces pbnds+: a novel physics-based neural deferred shading pipeline utilizing convolution neural networks to decrease the parameters and improve the performance in shading and relighting tasks; Energy regularization is also proposed to restrict the model reflection during dark illumination. Extensive experiments demonstrate that our approach outperforms classical baselines, a state-of-the-art neural shading model, and a diffusion-based method.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19522
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Convolutional Neural Deferred Shader for Physics Based Rendering
He, Zhuo
Ru, Yingdong
Liu, Qianying
Henderson, Paul
Pugeault, Nicolas
Computer Vision and Pattern Recognition
Recent advances in neural rendering have achieved impressive results on photorealistic shading and relighting, by using a multilayer perceptron (MLP) as a regression model to learn the rendering equation from a real-world dataset. Such methods show promise for photorealistically relighting real-world objects, which is difficult to classical rendering, as there is no easy-obtained material ground truth. However, significant challenges still remain the dense connections in MLPs result in a large number of parameters, which requires high computation resources, complicating the training, and reducing performance during rendering. Data driven approaches require large amounts of training data for generalization; unbalanced data might bias the model to ignore the unusual illumination conditions, e.g. dark scenes. This paper introduces pbnds+: a novel physics-based neural deferred shading pipeline utilizing convolution neural networks to decrease the parameters and improve the performance in shading and relighting tasks; Energy regularization is also proposed to restrict the model reflection during dark illumination. Extensive experiments demonstrate that our approach outperforms classical baselines, a state-of-the-art neural shading model, and a diffusion-based method.
title A Convolutional Neural Deferred Shader for Physics Based Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.19522