☆ 4.6 Article

Interactive neural cascade denoising for 1-spp Monte Carlo images

VISUAL COMPUTER (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Software Engineering

Human Dynamics from Monocular Video with Dynamic Camera Movements

Ri Yu et al.

Summary: The proposed method reconstructs 3D human motion from in-the-wild video by utilizing prior knowledge on physics laws, overcoming the limitation of static camera views to deal with dynamic view videos. By inferring body translations and rotations, the algorithm can simulate 3D human motion from a sequence of 3D full-body poses in the video.

ACM TRANSACTIONS ON GRAPHICS (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Ensemble Denoising for Monte Carlo Renderings

Shaokun Zheng et al.

Summary: This paper introduces an optimization-based ensemble denoising technique that combines multiple individual MC denoisers to clean up noise in renderings. The method computes optimal weights for combining output images from individual denoisers, and is shown to be effective and robust across various scenes and sample rates, outperforming individual denoisers. Additionally, a comprehensive analysis on selecting denoisers to be combined is provided for practical guidance.

ACM TRANSACTIONS ON GRAPHICS (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Path-based Monte Carlo Denoising Using a Three-Scale Neural Network

Weiheng Lin et al.

Summary: This paper introduces a new technique using deep learning methods for denoising in Monte Carlo rendering. By handling three scales of features, using an improved feature extractor, and feature attention mechanism, it achieves higher quality denoising results and better preservation of details compared to previous methods.

COMPUTER GRAPHICS FORUM (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Interactive Monte Carlo Denoising using Affinity of Neural Features

Mustafa Isik et al.

Summary: The study introduces a new learning-based denoiser that achieves state-of-the-art quality at interactive rates. By processing individual path-traced samples and extracting feature vectors, along with filtering noisy radiance using spatial kernels, the denoiser ensures temporally stable results.

ACM TRANSACTIONS ON GRAPHICS (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Real-time Neural Radiance Caching for Path Tracing

Thomas Muller et al.

Summary: The paper presents a real-time neural radiance caching method for path-traced global illumination, which is designed to handle fully dynamic scenes and achieve significant noise reduction while maintaining real-time performance. By utilizing adaptation training and self-training with simple iterative training updates, the method demonstrates state-of-the-art results on challenging scenarios without the need for pretraining.

ACM TRANSACTIONS ON GRAPHICS (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Real-time Monte Carlo Denoising with Weight Sharing Kernel Prediction Network

Hangming Fan et al.

Summary: This paper introduces a novel real-time Monte Carlo denoising method that encodes and reconstructs the kernel map efficiently to achieve real-time denoising of very low spp images. By utilizing a scalable kernel fusion module to improve denoising quality, the proposed approach significantly reduces the throughput of the kernel-prediction network.

COMPUTER GRAPHICS FORUM (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Denoising Monte Carlo renderings via a multi-scale featured dual-residual GAN

Yifan Lu et al.

Summary: The paper proposes a novel GAN structure for denoising Monte Carlo renderings by utilizing dual residual connections and multi-scale auxiliary features extraction method. By employing spatial-adaptive blocks with deformable convolution, the network adapts to spatial texture and edge features variance, achieving better visual effects and quantitative metrics compared to previous methods.

VISUAL COMPUTER (2021)

添加到收藏夹

Review Computer Science, Software Engineering

A survey on deep learning-based Monte Carlo denoising

Yuchi Huo et al.

Summary: Monte Carlo integration is commonly used in realistic image synthesis, but balancing bias and variance may result in noise. Recent focus has been on denoising MC rendering with deep learning, showing promising results in real-world applications.

COMPUTATIONAL VISUAL MEDIA (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Neural Supersampling for Real-time Rendering

Lei Xiao et al.

ACM TRANSACTIONS ON GRAPHICS (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Neural Temporal Adaptive Sampling and Denoising

J. Hasselgren et al.

COMPUTER GRAPHICS FORUM (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Neural Denoising with Layer Embeddings

Jacob Munkberg et al.

COMPUTER GRAPHICS FORUM (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Deep Combiner for Independent and Correlated Pixel Estimates

Jonghee Back et al.

ACM TRANSACTIONS ON GRAPHICS (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Blockwise Multi-Order Feature Regression for Real-Time Path-Tracing Reconstruction

Matias Koskela et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

添加到收藏夹

Article Computer Science, Software Engineering

Deep Convolutional Reconstruction For Gradient-Domain Rendering

Markus Kettunen et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

添加到收藏夹

Article Computer Science, Software Engineering

Sample-based Monte Carlo Denoising using a Kernel-Splatting Network

Michatel Gharbi et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

添加到收藏夹

Article Computer Science, Software Engineering

Computational LEGO® Technic Design

Hao Xu et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

添加到收藏夹

Article Computer Science, Software Engineering

Deep Adaptive Sampling for Low Sample Count Rendering

Alexandr Kuznetsov et al.

COMPUTER GRAPHICS FORUM (2018)

添加到收藏夹

Article Computer Science, Software Engineering

Denoising with Kernel Prediction and Asymmetric Loss Functions

Thijs Vogels et al.

ACM TRANSACTIONS ON GRAPHICS (2018)

添加到收藏夹

Article Computer Science, Software Engineering

Gradient Estimation for Real-Time Adaptive Temporal Filtering

Christoph Schied et al.

PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES (2018)

添加到收藏夹

Article Computer Science, Software Engineering

Interactive Reconstruction of Monte Carlo Image Sequences using a Recurrent Denoising Autoencoder

Chakravarty R. Alla Chaitanya et al.

ACM TRANSACTIONS ON GRAPHICS (2017)

添加到收藏夹

Article Computer Science, Software Engineering

A Machine Learning Approach for Filtering Monte Carlo Noise

Nima Khademi Kalantari et al.

ACM TRANSACTIONS ON GRAPHICS (2015)

添加到收藏夹

Article Computer Science, Software Engineering

Recent Advances in Adaptive Sampling and Reconstruction for Monte Carlo Rendering

M. Zwicker et al.

COMPUTER GRAPHICS FORUM (2015)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.