公开(公告)号：US20170116754A1

公开(公告)日：2017-04-27

申请号：US15333354

申请日：2016-10-25

Applicant: Imagination Technologies Limited

Inventor： James Imber ,  Adrian Hilton ,  Jean-Yves Guillemaut

IPC: G06T7/40 ,  G06K9/46 ,  G06T5/20

CPC classification number: G06T5/20 ,  G06K9/4661 ,  G06T7/11 ,  G06T7/90 ,  G06T15/506 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20028

Abstract: An image processing system and method for determining an intrinsic colour component of one or more objects for use in rendering the object(s) is described herein. One or more input images are received, each representing a view of the object(s), wherein values of each of the input image(s) are separable into intrinsic colour estimates and corresponding shading estimates. A depth image represents depths of the object(s). Coarse intrinsic colour estimates are determined using the input image(s). The intrinsic colour component is determined by applying bilateral filtering to the coarse intrinsic colour estimates using bilateral filtering guidance terms based on depth values derived from the depth image.

公开(公告)号：US09613431B2

公开(公告)日：2017-04-04

申请号：US14544123

申请日：2014-11-26

Applicant: Imagination Technologies Limited

Inventor： James Imber ,  Adrian Hilton ,  Jean-Yves Guillemaut

IPC: G06K9/00 ,  G06T7/40 ,  G06T7/00 ,  G06T15/04 ,  G06T15/06 ,  G06T15/10 ,  G06T15/50 ,  G06T11/00 ,  G06T11/60 ,  G06T15/80 ,  G06T17/00

CPC classification number: G06T7/90 ,  G06T7/507 ,  G06T11/001 ,  G06T11/60 ,  G06T15/04 ,  G06T15/06 ,  G06T15/10 ,  G06T15/50 ,  G06T15/80 ,  G06T17/00 ,  G06T2207/20224 ,  G06T2215/16

Abstract: Relightable free-viewpoint rendering allows a novel view of a scene to be rendered and relit based on multiple views of the scene from multiple camera viewpoints. Cast shadows in the scene are handled to allow local occlusion to be taken into account when determining irradiance estimates for the sample positions in the scene. This is achieved by determining an initial estimate of irradiance by ignoring local occlusion, then using that initial irradiance estimate with knowledge of the scene geometry to determine an angle-dependent radiance estimate for the scene. This radiance estimate can then be used with the knowledge of the scene geometry to determine local irradiance estimates at the sample positions within the scene.

公开(公告)号：US20250148264A1

公开(公告)日：2025-05-08

申请号：US19018414

申请日：2025-01-13

Applicant: Imagination Technologies Limited

Inventor： Ivaxi Sheth ,  Aria Ahmadi ,  James Imber ,  Cagatay Dikici

IPC: G06N3/045 ,  G06N3/08 ,  G06T1/20

Abstract: A windowed operation is implemented in at least three traversed dimensions. The windowed operation applies a window having at least three dimensions to data having at least three traversed dimensions, with shifts of the window in all three traversed dimensions. Two dimensions of the at least three traversed dimensions are selected, and the windowed operation is mapped to a plurality of constituent 2-D windowed operations in the selected two dimensions, the 2-D windowed operations applying a slice of the window to a slice of the data, with shifts of the slice of the window in only two dimensions. Each of the plurality of 2-D windowed operations is implemented by at least one hardware accelerator, each 2-D windowed operation producing a respective partial result, and the partial results are assembled to produce the result of the windowed operation.

公开(公告)号：US20250068883A1

公开(公告)日：2025-02-27

申请号：US18947580

申请日：2024-11-14

Applicant: Imagination Technologies Limited

Inventor： James Imber ,  Linling Zhang ,  Cagatay Dikici

IPC: G06N3/04 ,  G06F7/483 ,  G06F7/499 ,  G06F17/11 ,  G06N3/047 ,  G06N3/048 ,  G06N3/063

Abstract: Hierarchical methods for selecting fixed point number formats with reduced mantissa bit lengths for representing values input to, and/or output, from, the layers of a DNN. The methods begin with one or more initial fixed point number formats for each layer. The layers are divided into subsets of layers and the mantissa bit lengths of the fixed point number formats are iteratively reduced from the initial fixed point number formats on a per subset basis. If a reduction causes the output error of the DNN to exceed an error threshold, then the reduction is discarded, and no more reductions are made to the layers of the subset. Otherwise a further reduction is made to the fixed point number formats for the layers in that subset. Once no further reductions can be made to any of the subsets the method is repeated for continually increasing numbers of subsets until a predetermined number of layers per subset is achieved.

公开(公告)号：US12217161B2

公开(公告)日：2025-02-04

申请号：US17498618

申请日：2021-10-11

Applicant: Imagination Technologies Limited

Inventor： Clifford Gibson ,  James Imber

IPC: G06N3/063 ,  G06F7/00 ,  G06F7/544 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08

Abstract: A method of configuring a hardware implementation of a Convolutional Neural Network (CNN), the method comprising: determining, for each of a plurality of layers of the CNN, a first number format for representing weight values in the layer based upon a distribution of weight values for the layer, the first number format comprising a first integer of a first predetermined bit-length and a first exponent value that is fixed for the layer; determining, for each of a plurality of layers of the CNN, a second number format for representing data values in the layer based upon a distribution of expected data values for the layer, the second number format comprising a second integer of a second predetermined bit-length and a second exponent value that is fixed for the layer; and storing the determined number formats for use in configuring the hardware implementation of a CNN.

公开(公告)号：US12198307B2

公开(公告)日：2025-01-14

申请号：US17956778

申请日：2022-09-29

Applicant: Imagination Technologies Limited

Inventor： Szabolcs Cséfalvay ,  James Imber ,  David Walton ,  Insu Yu

IPC: G06T5/70 ,  G06T3/40 ,  G06T5/20 ,  G06T5/50 ,  G06T15/06 ,  G06T15/50

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image at a first resolution; obtaining one or more guide channels at the first resolution, and obtaining one or more corresponding guide channels at a second resolution. The second resolution may be the same resolution as, or a higher resolution than, the first resolution. For each of a plurality of local neighbourhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels (at the first resolution), and applying the calculated parameters to the one or more guide channels at the second resolution, to produce a denoised image at the second resolution.

公开(公告)号：US20240135507A1

公开(公告)日：2024-04-25

申请号：US18373855

申请日：2023-09-27

Applicant: Imagination Technologies Limited

Inventor： James Imber ,  Joseph Heyward ,  Kristof Beets

IPC: G06T5/73

CPC classification number: G06T5/73 ,  G06T2207/20021

Abstract: Methods and processing modules upsample a block of input pixels to determine a block of upsampled pixels. At least one of the upsampled pixels is a diagonal pixel, wherein a diagonal pixel is at a position that is not in any of the rows nor in any of the columns of input pixels in the block of input pixels. Indications of image gradients are determined for the block of input pixels. The determined indications of image gradients are used to determine one or more weighting parameters which are indicative of weights of a diagonal kernel. The upsampled pixels of the block of upsampled pixels are determined by applying kernels to the block of input pixels, wherein the diagonal pixel in the block of upsampled pixels is determined by applying the diagonal kernel to the block of input pixels in accordance with the determined one or more weighting parameters.

公开(公告)号：US20230195831A1

公开(公告)日：2023-06-22

申请号：US18096521

申请日：2023-01-12

Applicant: Imagination Technologies Limited

Inventor： Cagatay Dikici ,  Clifford Gibson ,  James Imber

IPC: G06F17/15 ,  G06N3/063

CPC classification number: G06F17/153 ,  G06N3/063

Abstract: Methods and systems for performing a convolution transpose operation between an input tensor having a plurality of input elements and a filter comprising a plurality of filter weights. The method includes: dividing the filter into a plurality of sub-filters; performing, using hardware logic, a convolution operation between the input tensor and each of the plurality of sub-filters to generate a plurality of sub-output tensors, each sub-output tensor comprising a plurality of output elements; and interleaving, using hardware logic, the output elements of the plurality of sub-output tensors to form a final output tensor for the convolution transpose.

公开(公告)号：US20230118937A1

公开(公告)日：2023-04-20

申请号：US17956778

申请日：2022-09-29

Applicant: Imagination Technologies Limited

Inventor： Szabolcs Csefalvay ,  James Imber ,  David Walton ,  Insu Yu

IPC: G06T15/06 ,  G06T5/00 ,  G06T3/40 ,  G06T5/50 ,  G06T5/20

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image at a first resolution; obtaining one or more guide channels at the first resolution, and obtaining one or more corresponding guide channels at a second resolution. The second resolution may be the same resolution as, or a higher resolution than, the first resolution. For each of a plurality of local neighbourhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels (at the first resolution), and applying the calculated parameters to the one or more guide channels at the second resolution, to produce a denoised image at the second resolution.

公开(公告)号：US20230114852A1

公开(公告)日：2023-04-13

申请号：US17956907

申请日：2022-09-30

Applicant: Imagination Technologies Limited

Inventor： Szabolcs Csefalvay ,  James Imber ,  David Walton ,  Insu Yu

IPC: G06T5/00 ,  G06T5/50 ,  G06T15/06 ,  G06T15/50 ,  G06T5/20

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image and obtaining one or more guide channels. For each of a plurality of local neighborhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels, and applying the calculated parameters to produce a denoised image. At least one of (i) the noisy image, (ii) the one or more guide channels, and (iii) the denoised image, are stored in a quantized low-bitdepth format.