摘要:
An encoder includes an encoder engine, a storage device and a controller to implement an iterative coding process. The encoder engine compresses a selected portion of a data sequence. The storage device stores the compressed portion of the data sequence after each iteration. The controller selects the portion of the data sequence to compress for each iteration. The controller gathers statistics from the compressed portion of the data sequence. The gathered statistics include statistics generated by the selected frames and statistics extrapolated from the selected frames for the non-selected frames. The controller adjusts coding parameters of the encoder engine on each iteration until the gathered statistics meet a specified performance requirement.
摘要:
A minimum sampling rate and a minimum sampling curve for continuous representation of a scene are disclosed. The minimum sampling rate for light-field rendering is determined in accordance with Δ t max = 1 2 K Ω v fh d , where K&OHgr;v accounts for a light-field signal cut-off frequency, a sampling camera resolution and an output resolution, ƒ specifies a sampling camera focal length, and hd specifies a light-field depth range. The minimum sampling curve for image-based rendering is determined as constrained by Nd=2K&OHgr;vƒhd&Dgr;t, Nd≧1, where Nd is the number of depth layers, &Dgr;t specifies a sampling interval along a t direction. Where IBR is be performed under uncertain depth, the curve is determined as Δ t max = min z e ( z e + Δ η ) ( z e - Δ η ) 4 fK Ω v Δ η , where &Dgr;tmax specifies a maximum sampling interval along a t direction, ze specifies an estimated depth, and &Dgr;&eegr; specifies a depth error.
摘要:
Techniques for encoding data based at least in part upon an awareness of the decoding complexity of the encoded data and the ability of a target decoder to decode the encoded data are disclosed. In some embodiments, a set of data is encoded based at least in part upon a state of a target decoder to which the encoded set of data is to be provided. In some embodiments, a set of data is encoded based at least in part upon the states of multiple decoders to which the encoded set of data is to be provided.
摘要:
A method of encoding a sequence of video images is described. The method receives the sequence of video images. The method iteratively examines different encoding solutions for the sequence of video images to identify an encoding solution that optimizes image quality while meeting a target bit rate and satisfying a set of constraints regarding flow of encoded data through an input buffer of a hypothetical reference decoder for decoding the encoded video sequence. The iterative examining includes, for each encoding solution, determining whether the hypothetical reference decoder underflows while processing the encoding solution for any set of images within the video sequence.
摘要:
Some embodiments provide a video recording device for capturing a video clip. The video recording device receives a selection of a non-temporally compressed encoding scheme from several different encoding schemes for encoding the video clip. The different encoding schemes include at least one temporally compressed encoding scheme and at least the selected non-temporally compressed encoding scheme. The video recording device captures the video clip as several frames. The video recording device non-temporally encodes each of the frames as several slices. The slices of a particular frame are for decoding by several processing units of a video decoding device. The video recording device stores the video clip in a storage.
摘要:
Output textures may be generated by synthesizing an input texture comprising discrete elements with a set of boundary conditions. Elements of the input texture are copied from the input texture to an output texture that is defined by a set of boundary conditions and are then refined. The elements of the output texture are refined by assigning domain and/or attribute information to the elements of the output texture element by minimizing an energy function measuring a similarity between output neighborhoods of the output texture and a corresponding best matching input neighborhood of the input texture.
摘要:
A method for constructing an avatar of a human subject includes acquiring a depth map of the subject, obtaining a virtual skeleton of the subject based on the depth map, and harvesting from the virtual skeleton a set of characteristic metrics. Such metrics correspond to distances between predetermined points of the virtual skeleton. In this example method, the characteristic metrics are provided as input to an algorithm trained using machine learning. The algorithm may be trained using a human model in a range of poses, and a range of human models in a single pose, to output a virtual body mesh as a function of the characteristic metrics. The method also includes constructing a virtual head mesh distinct from the virtual body mesh, with facial features resembling those of the subject, and connecting the virtual body mesh to the virtual head mesh.
摘要:
This invention is directed to a video bit rate control method for encoding a video sequence based on a decoder buffer condition and a group of picture (GOP) size limitation of the encoded video sequence. The method includes iteratively adjusting a quantization parameter and/or a masking strength parameter and encoding the video sequence at the adjusted parameters until the buffer condition and GOP size limitation are satisfied. The method makes the above adjustments to avoid buffer underflow and GOP oversizing.
摘要:
Embodiments for single-pass bounding box calculation are disclosed. In accordance with one embodiment, the single-pass bounding box calculation includes rendering a first target to a 2-dimensional screen space, whereby the first target includes at least six pixels. The calculation further includes producing transformed vertices in a set of geometry primitives based on an application-specified transformation. The calculation also includes generating six new points for each transformed vertex in the set of geometry primitives. The calculation additionally includes producing an initial third coordinate value for each pixel by rendering the at least six new points generate for each pixel to each corresponding pixel. The calculation further includes producing a post-rasterization value for each pixel by rasterizing the at least six new points rendered to each pixel with each corresponding pixel. Finally, the calculation includes computing bounding box information for the set of geometry primitives based on the produced third coordinate values.
摘要:
Some embodiments of the invention provide a multi-pass encoding method that encodes several images (eg., several frames of a video sequence). The method iteratively performs an encoding operation that encodes these images. The encoding operation is based on a nominal quantization parameter, which the method uses to compute quantization parameters for the images. During several different iterations of the encoding operation, the method uses several different nominal quantization parameters. The method stops its iterations when it reaches a terminating criterion (e.g., it identifies an acceptable encoding of the images).