Image analytics using artificial intelligence : pose guided human image generation with deep neural network
Given the widespread problems of gelatinization and texture loss in the current image generation, a pose-guided human image generation model with RFB (Receptive Field Block) and SE (Squeeze-and-Excitation) Module added is proposed. This model uses GAN (Generative Adversarial Network) for training. I...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/150150 |
| _version_ | 1826129650185666560 |
|---|---|
| author | Nie, Li |
| author2 | Yap Kim Hui |
| author_facet | Yap Kim Hui Nie, Li |
| author_sort | Nie, Li |
| collection | NTU |
| description | Given the widespread problems of gelatinization and texture loss in the current image generation, a pose-guided human image generation model with RFB (Receptive Field Block) and SE (Squeeze-and-Excitation) Module added is proposed. This model uses GAN (Generative Adversarial Network) for training. It is used in pose integration and image refinement. Inspired by the attention mechanism of the channel feature, it is advisable to put the SE Module into the encoder block of Generator1 and Generator2. In addition, it also puts RFB into the forward layer of Generator1 and Generator2. It aims at enhancing the robustness of the image generation model and improve the quality of the produced image. The experimental results illustrate that the proposed model can obtain a higher evaluation score. It generates a more realistic and delicate human pose image that conforms to visual perception. |
| first_indexed | 2024-10-01T07:43:59Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/150150 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:43:59Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1501502023-07-07T18:34:48Z Image analytics using artificial intelligence : pose guided human image generation with deep neural network Nie, Li Yap Kim Hui School of Electrical and Electronic Engineering EKHYap@ntu.edu.sg Engineering::Electrical and electronic engineering Given the widespread problems of gelatinization and texture loss in the current image generation, a pose-guided human image generation model with RFB (Receptive Field Block) and SE (Squeeze-and-Excitation) Module added is proposed. This model uses GAN (Generative Adversarial Network) for training. It is used in pose integration and image refinement. Inspired by the attention mechanism of the channel feature, it is advisable to put the SE Module into the encoder block of Generator1 and Generator2. In addition, it also puts RFB into the forward layer of Generator1 and Generator2. It aims at enhancing the robustness of the image generation model and improve the quality of the produced image. The experimental results illustrate that the proposed model can obtain a higher evaluation score. It generates a more realistic and delicate human pose image that conforms to visual perception. Bachelor of Engineering (Electrical and Electronic Engineering) 2021-06-12T13:05:19Z 2021-06-12T13:05:19Z 2021 Final Year Project (FYP) Nie, L. (2021). Image analytics using artificial intelligence : pose guided human image generation with deep neural network. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/150150 https://hdl.handle.net/10356/150150 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Nie, Li Image analytics using artificial intelligence : pose guided human image generation with deep neural network |
| title | Image analytics using artificial intelligence : pose guided human image generation with deep neural network |
| title_full | Image analytics using artificial intelligence : pose guided human image generation with deep neural network |
| title_fullStr | Image analytics using artificial intelligence : pose guided human image generation with deep neural network |
| title_full_unstemmed | Image analytics using artificial intelligence : pose guided human image generation with deep neural network |
| title_short | Image analytics using artificial intelligence : pose guided human image generation with deep neural network |
| title_sort | image analytics using artificial intelligence pose guided human image generation with deep neural network |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/150150 |
| work_keys_str_mv | AT nieli imageanalyticsusingartificialintelligenceposeguidedhumanimagegenerationwithdeepneuralnetwork |