Qualcomm Incorporated

Auke Joris Wiggers

Dana Kianfar

Marta Karczewicz

Jianle Chen

Ahmed Kamel Sadek

Hongtao Wang

Taco Sebastiaan Cohen

Mohammad Naghshvar

Guillaume Konrad Sautiere

Anand Meher Kotra

Amir Said

Reza Pourreza

Venkata Meher Satchit Anand Kotra

Reza Pourreza Shahri

Hoang Cong Minh Le

Yunfan Zhang

Gabriele Cesa

Noor Fathima Khanum Mohamed Ghouse

Jens Petersen

Tianlin Xu

David Wilson Romero Guzman

Systems and techniques are described for processing image data using a residual model that can be configured with an adjustable number of sampling steps. For example, a process can include obtaining a latent representation of an image and processing, using a decoder of a machine learning model, the latent representation of the image to generate an initial reconstructed image. The process can further include processing, using the residual model, the initial reconstructed image and noise data to predict a plurality of predictions of a residual over a number of sampling steps. The residual represents a difference between the image and the initial reconstructed image. The process can include obtaining, from the plurality of predictions of the residual, a final residual representing the difference between the image and the initial reconstructed image. The process can further include combining the initial reconstructed image and the residual to generate a final reconstructed image.

Diffusion-based data compression

Certain aspects of the present disclosure provide techniques and apparatus for encoding content using a neural network. An example method generally includes encoding video content into a latent space representation through an encoder implemented by a first machine learning model. A code is generated by upsampling the latent space representation of the video content. A prior is calculated based on a conditional probability of obtaining the upsampled latent space representation conditioned by the latent space representation of the video content. A compressed version of the video content is generated based on a probabilistic model implemented by a second machine learning model, the generated code, and the calculated prior, and the compressed version of the video content is output for transmission.

Alias-free compression of content using artificial neural networks

An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a picture of video data; code a value for a syntax element representing a neural network model to be used to filter a portion of the decoded picture, the value representing an index into a set of pre-defined neural network models, the index corresponding to the neural network model in the set of pre-defined neural network models; and filter the portion of the decoded picture using the neural network model corresponding to the index.

Multiple neural network models for filtering during video coding

Systems and techniques are provided for coding video data based on an optical flow correction and a residual correction. For example, a decoding device can obtain a frame of encoded video data associated with an input frame, the frame of encoded video data including an optical flow correction and a residual correction. A predicted optical flow can be generated based on one or more reference frames and a reference optical flow. A corrected prediction frame can be generated based on the predicted optical flow and the optical flow correction. A predicted residual can be generated based on at least the corrected prediction frame and a first reference frame included in the one or more reference frames. The decoding device can generate a reconstructed input frame based on the corrected prediction frame, the predicted residual, and the residual correction.

Video coding using optical flow and residual predictors

A video encoder determines scaled transform coefficients, wherein determining the scaled transform coefficients comprises scaling transform coefficients of a block of the video data according to a given quantization step. The video encoder determines scalar quantized coefficients, wherein determining the scalar quantized coefficients comprises applying scalar quantization to the scaled transform coefficients of the block. Additionally, the video encoder applies a neural network that determines a respective set of probabilities for each respective transform coefficient of the block. The respective set of probabilities for the respective transform coefficient includes a respective probability value for each possible adjustment value in a plurality of possible adjustment values. Inputs to the neural network include the scaled transform coefficients and the scalar quantized coefficients. The video encoder determines, based on the set of probabilities for a particular transform coefficient of the block, a quantization level for the particular transform coefficient.

Parallelized rate-distortion optimized quantization using deep learning

A method includes determining a current state of an environment of an autonomous agent, such as a vehicle. The method also includes determining, via a first neural network, a set of actions based on the current state. The method further includes determining whether further analysis of the set of actions is desired. The method selects an action from the set of actions using a model-based solution based on a reward and a risk of the action when further analysis is desired. The method also includes selecting the action from the set of actions according to a metric when further analysis is not desired. The method controls the autonomous agent to perform the selected action.

Hybrid reinforcement learning for autonomous driving

Growing community of inventors

Amsterdam, Netherlands

Auke Joris Wiggers