US 12,001,959 B2
Neural network model training method and device, and time-lapse photography video generating method and device
Wenhan Luo, Shenzhen (CN); Lin Ma, Shenzhen (CN); and Wei Liu, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Jul. 14, 2022, as Appl. No. 17/864,730.
Application 17/864,730 is a continuation of application No. 16/892,587, filed on Jun. 4, 2020, granted, now 11,429,817.
Application 16/892,587 is a continuation of application No. PCT/CN2019/076724, filed on Mar. 1, 2019.
Claims priority of application No. 201810253848.3 (CN), filed on Mar. 26, 2018.
Prior Publication US 2022/0366193 A1, Nov. 17, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/088 (2023.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2023.01); G06T 15/20 (2011.01); G06V 20/40 (2022.01)
CPC G06N 3/088 (2013.01) [G06F 18/214 (2023.01); G06F 18/2193 (2023.01); G06N 3/045 (2023.01); G06V 20/41 (2022.01); G06V 20/49 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating a time-lapse photography video with a neural network model, the method comprising:
obtaining, by a device comprising a memory storing instructions and a processor in communication with the memory, a training sample, the training sample comprising a training video and an image set corresponding to the training video;
obtaining, by the device, a basic time-lapse photography video by using a first generative adversarial network of a neural network model;
obtaining, by the device, an optimized time-lapse photography video based on the basic time-lapse photography video by using a generator in a second generative adversarial network of the neural network model;
obtaining, by the device, a discrimination result according to the optimized time-lapse photography video by using a discriminator in the second generative adversarial network;
generating, by the device, a loss of the second generative adversarial network according to the optimized time-lapse photography video, the basic time-lapse photography video, the training video, and the discrimination result, the loss comprising a ranking loss determined according to motion features respectively corresponding to the optimized time-lapse photography video, the basic time-lapse photography video, and the training video; and
optimizing, by the device, a set of network parameters of the second generative adversarial network according to the loss of the second generative adversarial network, until a training ending condition is satisfied.