Abstract: Certain aspects of the present disclosure provide techniques for adaptive sampling for rendering using deep learning. This includes receiving, at a sampler in a rendering pipeline, a plurality of rendered pixel data, wherein the sampler includes a first machine learning (ML) model. It further includes generating a sampling map for the rendering pipeline using the first ML model and the plurality of rendered pixel data, including predicting a plurality of pixel values in the sampling map based on a generated distribution of pixel values. It further includes rendering an image using the sampler, the sampling map, and a denoiser in the rendering pipeline.

Abstract: A system for execution of limit trades on decentralized exchanges comprising a computer service system configured for receiving from a client device a limit order for swapping a desired quantity of a first digital asset for a second digital asset at a desired target price. A smart contract on a blockchain network is then generated corresponding to the order. By depositing the desired quantity of the first digital asset the smart contracts creates a single-sided liquidity pool on the blockchain network. For real-time monitoring of price feeds the smart contract interacts with a decentralized oracle system. On finding one or more matches for the swapping at said target price the position is filled using liquidity pool. User receives the exact number of the second digital asset which the user wanted at the target price in exchange of the first digital asset without any price impact, liquidity fee or slippage.

Abstract: Techniques are disclosed for training and applying a denoising model. The denoising model includes multiple specialized denoisers and a generalizer, each of which is a machine learning model. The specialized denoisers are trained to denoise images associated with specific ranges of noise parameters. The generalizer is trained to generate per-pixel denoising kernels for denoising images associated with arbitrary noise parameters using outputs of the specialized denoisers. Subsequent to training, a noisy image, such as a live-action image or a rendered image, can be denoised by inputting the noisy image into the specialized denoisers to obtain intermediate denoised images that are then input, along with the noisy image, into the generalizer to obtain per-pixel denoising kernels, which can be normalized and applied to denoise the noisy image.