Deep adaptive sampling and reconstruction using analytic distributions
We propose an adaptive sampling and reconstruction method for offline Monte Carlo
rendering. Our method produces sampling maps constrained by a user-defined budget that …
rendering. Our method produces sampling maps constrained by a user-defined budget that …
Neural partitioning pyramids for denoising monte carlo renderings
Recent advancements in hardware-accelerated raytracing made it possible to achieve
interactive framerates even for algorithms previously considered offline, such as path …
interactive framerates even for algorithms previously considered offline, such as path …
Empowering convolutional neural nets with metasin activation
F Salehi, T Aydin, A Gaillard… - Advances in Neural …, 2023 - proceedings.neurips.cc
ReLU networks have remained the default choice for models in the area of image prediction
despite their well-established spectral bias towards learning low frequencies faster, and …
despite their well-established spectral bias towards learning low frequencies faster, and …
Automatic feature selection for denoising volumetric renderings
We propose a method for constructing feature sets that significantly improve the quality of
neural denoisers for Monte Carlo renderings with volumetric content. Starting from a large …
neural denoisers for Monte Carlo renderings with volumetric content. Starting from a large …
Neural Denoising for Deep‐Z Monte Carlo Renderings
We present a kernel‐predicting neural denoising method for path‐traced deep‐Z images
that facilitates their usage in animation and visual effects production. Deep‐Z images …
that facilitates their usage in animation and visual effects production. Deep‐Z images …
Joint self-attention for denoising Monte Carlo rendering
G Oh, B Moon - The Visual Computer, 2024 - Springer
Image-space denoising of rendered images has become a commonly adopted approach
since this post-rendering process often drastically reduces required sample counts (thus …
since this post-rendering process often drastically reduces required sample counts (thus …
Deep Compositional Denoising on Frame Sequences
We propose a novel extension for processing frame sequences that provides context from
neighboring frames while avoiding redundant computation and a novel quantization …
neighboring frames while avoiding redundant computation and a novel quantization …
An improved monte carlo denoising algorithm based on kernel-predicting convolutional network
J Liu, F Zuo, G Wang - … Conference on Web Information Systems and …, 2022 - Springer
Monte Carlo (MC) path tracing renders images with severe noise under one-sample-per-
pixel conditions, and one of the challenges of denoising is to achieve high rendering quality …
pixel conditions, and one of the challenges of denoising is to achieve high rendering quality …
[PDF][PDF] Empowering convolutional neural networks with MetaSin activation
F Salehi, TO Aydın, A Gaillard… - Proceedings of the …, 2023 - researchgate.net
RELU networks have remained the default choice for models in the area of image prediction
despite their well-established spectral bias towards learning low frequencies faster, and …
despite their well-established spectral bias towards learning low frequencies faster, and …
Robust Average Networks for Monte Carlo Denoising
J Kalojanov, K Thurston - arXiv preprint arXiv:2310.04080, 2023 - arxiv.org
We present a method for converting denoising neural networks from spatial into spatio-
temporal ones by modifying the network architecture and loss function. We insert Robust …
temporal ones by modifying the network architecture and loss function. We insert Robust …