Monte Carlo (MC) integration is used ubiquitously in realistic image synthesis because of its
flexibility and generality. However, the integration has to balance estimator bias and …

Various denoising methods have been proposed to clean up the noise in Monte Carlo (MC)
renderings, each having different advantages, disadvantages, and applicable scenarios. In …

Retransmission interference in radar and communication signal processing significantly
threatens the received linear frequency modulation signal. With the advancement in the …

Gradient‐domain rendering can highly improve the convergence of light transport simulation
using the smoothness in image space. These methods generate image gradients and solve …

针对铁轨缺陷检测神经网络模型参数多, 计算量大的问题, 提出了一种基于知识蒸馏的轨道检测
轻量化模型及其训练方法, 该网络模型由六层卷积层和三层全连接层构成, 将训练好的DenseNet …

This paper deals with the highly challenging problem of reconstructing the shape of a
refracting object from a single image of its resulting caustic. Due to the ubiquity of …

As the demand for high-quality rendering for mixed reality, videogame, and simulation has
increased, global illumination has been actively researched. Monte Carlo path tracing can …

This paper introduces the two-step process of the standard photon mapping algorithm and a
variety of other global biased illumination algorithms using photon mapping that have been …

Recently, deep learning-based approaches have led to dramatic improvements for Monte
Carlo rendering at the low sampling rate. Most of these approaches are aimed at path …

Photon mapping is a light transport algorithm that simulates various rendering effects (eg,
caustics) robustly, and its progressive variants, progressive photon mapping (PPM) …