TY - GEN
T1 - Controllable Person Image Synthesis GAN and Its Reconfigurable Energy-efficient Hardware Implementation
AU - Lin, Shaoyue
AU - Zhang, Yanjun
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/3/4
Y1 - 2022/3/4
N2 - At this stage, how to controllably generate higher quality person image is still the challenge of person image synthesis. At the same time, the update of image synthesis network is far ahead of its hardware implementation. Therefore, this paper proposes a GAN network for person image synthesis that can generate high quality person image with controllable pose and attributes. The newly designed network is more convenient for hardware implementation while ensuring that the generated image is controllable. This paper also designs a synthesizable library for GAN to pursue faster hardware reconfiguration. We completed the new model proposed in this paper based on this library. Finally, the proposed network achieves better results both quantitatively and qualitatively compared with previous work. Compared with GPU and CPU, the hardware implementation based on FPGA can achieve the highest energy efficient of 73.67 GOPS / W.
AB - At this stage, how to controllably generate higher quality person image is still the challenge of person image synthesis. At the same time, the update of image synthesis network is far ahead of its hardware implementation. Therefore, this paper proposes a GAN network for person image synthesis that can generate high quality person image with controllable pose and attributes. The newly designed network is more convenient for hardware implementation while ensuring that the generated image is controllable. This paper also designs a synthesizable library for GAN to pursue faster hardware reconfiguration. We completed the new model proposed in this paper based on this library. Finally, the proposed network achieves better results both quantitatively and qualitatively compared with previous work. Compared with GPU and CPU, the hardware implementation based on FPGA can achieve the highest energy efficient of 73.67 GOPS / W.
KW - FPGA
KW - GAN
KW - person image synthesis
UR - http://www.scopus.com/inward/record.url?scp=85131898665&partnerID=8YFLogxK
U2 - 10.1145/3529466.3529500
DO - 10.1145/3529466.3529500
M3 - Conference contribution
AN - SCOPUS:85131898665
T3 - ACM International Conference Proceeding Series
SP - 154
EP - 160
BT - ICIAI 2022 - 6th International Conference on Innovation in Artificial Intelligence
PB - Association for Computing Machinery
T2 - 6th International Conference on Innovation in Artificial Intelligence, ICIAI 2022
Y2 - 4 March 2022 through 6 March 2022
ER -