Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder

356 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content (2018, methodology): “…imaging, neural networks have been used for predicting sky illumination for rendering [SBRCD17, HGSH ∗ 17], denoising Monte Carlo renderings [KBS15, CKS ∗ 17, BVM ∗ 17], predicting HDR environment maps [ZL17a], reducing artefacts such as ghosting when fusing multiple LDR exposures to create HDR…”
Neural Inverse Rendering of an Indoor Scene From a Single Image (2019, methodology): “(3) We utilize deep denoising [3], which allows us to render high-quality images from limited samples per pixel.”
Advances in Neural Rendering (2021, background): “We also do not cover neural super-sampling and denoising methods for ray-traced imagery [CKS ∗ 17,KBS15].”
Data-driven synthesis of smoke flows with CNN-based feature descriptors (2017, unknown): “While previous work shows that warping layers are useful in motion field learning [Chen et al. 2017; de Bezenac et al. 2017], our work targets the opposite direction: by providing our networks with velocities, warping layers can likewise improve the training of temporally coherent content generation”
Kernel-predicting convolutional networks for denoising Monte Carlo renderings (2017, background): “A similar gure in concurrent work [Chaitanya et al. 2017] allows readers to see the relative improvements over the baseline, facilitating comparisons of these two systems.”