Granted Patent B2

US 12,015,776 · App. 18/230,314 · Granted Jun 18, 2024

Inventors: Chri Besenbruch (London, GB); Ciro Cursio (London, GB); Christopher Finlay (London, GB); Vira Koshkina (London, GB); Alexander Lytchier (London, GB); Jan Xu (London, GB); Arsalan Zafar (London, GB)

Assignee: DEEP RENDER LTD.

H04N19/126G06N3/045G06N3/084G06T3/4046G06T9/002G06V10/774H04N19/13

Abstract

Claims (28)

1. Computer implemented method of training a first neural network and a second neural network, the neural networks being for use in lossy image or video compression, transmission and decoding, the method including the steps of:

(i) receiving a plurality of input training images associated with a corresponding plurality of views of a scene;

(ii) encoding the plurality of input training images using the first neural network, to produce a latent representation;

(iii) quantizing the latent representation to produce a quantized latent;

(iv) using the second neural network to produce a plurality of output images associated with said corresponding plurality of views from the quantized latent, wherein the plurality of output images are an approximation of the plurality of input images;

(v) evaluating a loss function based on differences between the plurality of output images and the plurality of input images;

(vi) evaluating a gradient of the loss function;

(vii) back-propagating the gradient of the loss function through the second neural network and through the first neural network, to update weights of the second neural network and of the first neural network; and

(viii) repeating steps (i) to (vii) using a set of said plurality of input training images, to produce a trained first neural network and a trained second neural network, and

(ix) storing the weights of the trained first neural network and of the trained second neural network.

2. The method of claim 1 , wherein the loss function is evaluated as a weighted sum of differences between the output images and the input training images, and the estimated bits of the quantized image latents.

3. The method of claim 1 , wherein the steps of the method are performed by a computer system.

4. The method of claim 1 , wherein the loss function includes using a single image depth-map estimation of the plurality of input training images and the plurality of output images and then measuring the distortion between the depth maps of the plurality of input training images and the plurality of output images.

5. The method of claim 1 , wherein the loss function includes using a reprojection into a 3-d coordinate system using said plurality of input training images and a reprojection into the 3-d coordinate system using said plurality of output images and a loss measuring the difference of the resulting 3-d coordinate systems.

6. The method of claim 1 , wherein the loss function includes using optical flow methods that establish correspondence between pixels in said plurality of input training images and said plurality of output images and a loss to minimise one or more flow-maps.

7. The method of claim 1 , wherein positional location information associated with one or more cameras associated with the plurality of input images and their absolute or relative configuration are encoded in the neural networks as a prior through the training process.

8. A computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of:

(i) receiving a plurality of input images associated with a corresponding plurality of views of a scene at a first computer system;

(ii) encoding the plurality of input images using a first trained neural network trained according to the method of claim 6 , using the first computer system, to produce a latent representation;

(iii) quantizing the latent representation using the first computer system to produce a quantized latent;

(iv) entropy encoding the quantized latent into a bitstream, using the first computer system;

(v) transmitting the bitstream to a second computer system;

(vi) the second computer system entropy decoding the bitstream to produce the quantized latent;

(vii) the second computer system using a second trained neural network trained according to the method of claim 1 , to produce a plurality of output images associated with said plurality of views from the quantized latent, wherein the plurality of output images are an approximation of the plurality of input images.

9. The method of claim 8 , wherein in step (vii) the output images are stored.

10. The method of claim 8 , wherein ground-truth dependencies between the plurality of input images are used as additional input to the first neural network.

11. The method of claim 8 , wherein depth maps associated with the plurality of input images are used as additional input to the first neural network.

12. The method of claim 8 , wherein optical flow data associated with the plurality of input images are used as additional input to the first neural network.

Assignments (1)

Priority Claims (12)

Continuity (6)

Cited By (4)

US 12,327,382 US 12,382,051 US 12,437,448 US 12,542,141