Abstract: A method, computer program, and computer system is provided for coding video data. Video data including one or more subpictures is received. A number of the subpictures and a delta value between the number of subpictures and a number of rectangular slices are signaled. The number of rectangular slices is derived based on the number of subpictures and the delta value.

Abstract: A method of decoding an encoded video bitstream using at least one processor includes obtaining a video coding layer (VCL) network abstraction layer (NAL) unit; determining whether the VCL NAL unit is a first VCL NAL unit of a picture unit (PU) containing the VCL NAL unit; based on determining that the VCL NAL unit is the first VCL NAL unit of the PU, determining whether the VCL NAL unit is a first VCL NAL unit of an access unit (AU) containing the PU; and based on determining that the VCL NAL unit is the first VCL NAL unit of the AU, decoding the AU based on the VCL NAL unit.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive an audio signal obtained from a microphone, input the audio signal into a neural-network pipeline, the neural-network pipeline including a convolutional network that receives the audio signal and provides a first output of the convolutional network to an enhancer, the enhancer including a deep complex convolutional recurrent network that receives the first output along with a mel spectrogram of the audio signal and outputs a second output to at least one of a vocoder and a decoder, and control an output of an enhanced audio signal from the at least one of the vocoder and the decoder.

Abstract: A method of hair rendering includes acquiring a color input image and an opacity input image from a hair rendering system, the color input image and the opacity input image having a first sample resolution. The method further includes providing the color input image and the opacity input image as input to a trained neural network configured to generate an intermediate color output image and an intermediate opacity output image by performing an anti-aliasing function on the color input image and the opacity input image. The method further includes performing hair rendering based on the intermediate color output image and the intermediate opacity output image to generate a final rendered hair image.

Abstract: A method performed by at least one processor of an acoustic howling suppression (AHS) system includes receiving, from an input source device, an audio signal. The method includes refining one or more parameters of a Kalman filter based on one or more neural networks. The method includes filtering the audio signal using the Kalman filter with the one or more refined parameters of the Kalman filter to reduce acoustic howling included in the audio signal.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive multiple audio signals obtained from ones of a plurality of microphones of a microphone array, implement an audio zooming based on the audio signals by selectively focusing and enhancing first ones of the audio signals and by attenuating other ones of the audio signals, and control an output of audio based on the audio zooming, and the audio zooming includes a consolidating of a plurality of directional features of the first ones of the audio signals within a field around the microphone array and a countering based on determining directional aspects of the other ones of the audio signals from outside of the field.

Abstract: One or more template predictions are generated for a template of a current block based on one or more prediction modes. The template includes neighboring samples of the current block. Each of the one or more template predictions is generated based on a respective one of the one or more prediction modes. One or more filters are derived for the current block. Each of the one or more filters is derived based on (i) filter index information or (ii) a respective one of the one or more template predictions and a template reconstruction of the template. One or more predictions of the current block are determined. Each of the one or more predictions is determined based on a respective one of the one or more prediction modes. A final prediction of the current block is determined by applying the one or more filters to the one or more predictions.

Abstract: A method and an apparatus for video decoding are disclosed. The apparatus includes processing circuitry that decodes prediction information of a current block that is indicative of an intra block copy mode. The current block is in a current region of a plurality of regions of a current coding tree unit (CTU) in a current picture. The processing circuitry determines a block vector for the current block, a reference block indicated by the block vector being in a search range that excludes at least a region in a previously reconstructed CTU that is collocated with the current region of the current CTU, a position of the collocated region in the previously reconstructed CTU having a same relative position as the current region in the current CTU, the search range being in the current picture. The processing circuitry reconstructs at least one sample of the current block according the block vector.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive an input question to the LLM, model an advantage for the input question based on at least one of a multi-gaussian mixed matrix (GMM) model and an entropy regularizer, and train the LLM based on the advantage, and the advantage includes a proximal policy optimization (PPO) objective where modeling the advantage is based on the multi-GMM model, and the advantage includes a combination of an output of a reward model (RM) and an average model performance for the input question where modeling the advantage is based on the entropy regularizer.

Abstract: The disclosure includes methods and an apparatus that includes processing circuitry that selects at least one candidate surrogate metric from a plurality of surrogate metrics based on first testing data of a target metric and the plurality of surrogate metrics from a first database in memory. The first testing data have been generated from previously controlled testing of a control variant and a treatment variant of a feature of a webpage or a computer application. The processing circuitry determines current testing results associated with the plurality of surrogate metrics and determines an output of the current controlled testing based on one or more of the current testing results associated with the at least one candidate surrogate metric. If the output indicates the treatment variant replacing the control variant of the feature of the webpage or the computer application, the control variant is replaced with the treatment variant of the feature.

Abstract: A method includes receiving a bitstream that comprises coded information of a current block, the coded information of the current block indicates a state transition path of a state machine, the state transition path of the state machine includes at least a first state transition associated with a first quantization shifting offset of one or more first transform coefficients in transform coefficients of the current block. The method also includes determining the first quantization shifting offset associated with the one or more first transform coefficients according to the first state transition; reconstructing the one or more first transform coefficients based on the first quantization shifting offset; calculating residuals in a spatial domain of the current block based on at least the one or more first transform coefficients; and reconstructing the current block according to the residuals in the spatial domain.

Abstract: A coded video bitstream comprising a current block in a current picture is received. The current block includes a plurality of subblocks and is to be predicted by a subblock-based template matching motion vector prediction (SbTMVP) mode. A respective collocated reference subblock for each subblock is determined based on a combination of a displacement vector (DV) and a motion vector offset (MVO) that are associated with the respective subblock. A motion vector (MV) field in the respective collocated reference subblock of each subblock in the current block is determined. A respective reference template for each subblock is derived based on the determined MV field of the collocated reference subblock. The plurality of subblocks of the current block is reconstructed by predicting each subblock using the respective reference template in the SbTMVP mode.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain an input mesh comprising volumetric data of at least one three-dimensional (3D) visual content, derive a plurality of submeshes of the input mesh from a frame of the volumetric data, set bitdepths to a first submesh and a second submesh from the submeshes, a first bitdepth being different than a second bitdepth, quantize the first submesh and the second submesh based on respective ones of the first bitdepth and the second bitdepth, and signal a result of quantizing the first submesh and the second submesh.

Abstract: Aspects of the disclosure provide methods and apparatuses for video coding. In some examples, an apparatus includes processing circuitry. The processing circuitry obtains prediction information of a first block in a picture from a coded video bitstream, and generates reconstructed samples of the first block according to the prediction information and one of bi-directional prediction and uni-directional prediction. The processing circuitry adds motion information and a bi-prediction weight index of a History-based Motion Vector Prediction (HMVP) candidate to an HMVP list based on the prediction information of the first block and whether the first block is coded according to the bi-directional prediction or the uni-directional prediction. Further, the processing circuitry generates reconstructed samples of a second block in the picture based on a plurality of candidates that includes the HMVP candidate.

Abstract: A method is provided for controlling virtual units in a virtual scene at a computing device. The method includes, in response to receiving a first user input, displaying, on a display device, a first user interface (UI) that includes a plurality of command elements, the plurality of command elements comprising a union set of virtual unit actions performable by each user controllable virtual unit available to a user in the virtual scene. The method also includes receiving a second user input indicating a selection of a command element among the plurality of command elements in the first UI. The method further includes controlling one or more virtual units in the virtual scene to execute an action corresponding to the selected command element, the one or more virtual units being selected according to the first user input.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform parsing at least one video parameter set comprising at least one syntax element indicating whether at least one layer in the scalable bitstream is one of a dependent layer of the scalable bitstream and an independent layer of the scalable bitstream, coding a picture in the dependent layer by parsing and interpreting an inter-layer reference picture list, and coding a picture in an independent layer without parsing and interpreting the inter-layer reference picture list.

Abstract: Neural network based substitutional end-to-end (E2E) image compression (NIC) being performed by at least one processor and includes receiving an input image to an E2E NIC framework, determining a substitute image based on a training model of the E2E NIC framework, encoding the substitute image to generate a bitstream, mapping the substitute image to the bitstream to generate a compressed representation of the input image. Further, the input may be partitioned into blocks for which a substitute representation is determined for each block and each block is encoded instead of the entire substitute image.

Abstract: Aspects of the disclosure provide methods and apparatuses for video coding. In some examples, an apparatus includes processing circuitry configured to encode a first block in a picture according to one of bi-directional prediction and uni-directional prediction. The processing circuitry is configured to add motion information and a bi-prediction weight index of a History-based Motion Vector Prediction (HMVP) candidate to an HMVP list based on whether the first block is encoded according to the bi-directional prediction or the uni-directional prediction, the bi-prediction weight index indicating bi-prediction weights of the bi-directional prediction for the first block when the first block is encoded according to the bi-directional prediction, and the bi-prediction weight index indicating a default value when the first block is encoded according to the uni-directional prediction.

Abstract: A method including segmenting a multidimensional media stream into a plurality of segments of multidimensional media in a multidimensional space; splitting the segmented multidimensional media stream into a plurality of sub-streams that are capable of being processed in parallel, wherein each of the plurality of sub-streams comprises a segment metadata that is used for ordering the segments within the each sub-stream; processing each of the plurality of sub-streams in parallel; and merging the plurality of sub-streams into a single stream using the segment metadata carried to an output segment, wherein the single stream comprises ordered segments.

Abstract: The various implementations described herein include methods and systems for coding video. In one aspect, a method includes determining whether multiple transform units are within the video block in accordance with a determination that the inter-prediction mode is enabled; and in accordance with a determination that multiple transform units are within the video block: determining a transform unit of the multiple transform units to apply a secondary transform based on a relative location of the transform unit within the video block, applying the secondary transform to the transform unit, and reconstructing/processing the video block based at least on the secondary transform.