Painterly Image Harmonization in Dual Domains

Authors: Junyan Cao, Yan Hong, Li Niu

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on the benchmark dataset show the effectiveness of our method. Our code and model are available at https:// github.com/bcmi/PHDNet-Painterly-Image-Harmonization.
Researcher Affiliation Academia Mo E Key Lab of Artificial Intelligence, Shanghai Jiao Tong University {joy c1, ustcnewly}@sjtu.edu.cn, yanhong.sjtu@gmail.com
Pseudocode No The paper describes the method using textual descriptions and mathematical equations but does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes Our code and model are available at https:// github.com/bcmi/PHDNet-Painterly-Image-Harmonization.
Open Datasets Yes We conduct experiments on COCO (Lin et al. 2014) and Wiki Art (Tan et al. 2019).
Dataset Splits No The paper mentions using COCO and Wiki Art datasets but does not explicitly provide details on train/validation/test splits with specific percentages or sample counts for model training within the main text. It states 'Refer to the Supplementary for more implementation details.'
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU models, CPU types) used for running the experiments.
Software Dependencies No The paper states 'Refer to the Supplementary for more implementation details' but does not specify software dependencies (e.g., library names with version numbers like Python 3.8, PyTorch 1.9) within the main text.
Experiment Setup Yes So far, the total loss for training G is summarized as LG = Ls + λc Lc + λadv LGadv, (6) where the trade-off parameters λc and λadv are set to 2 and 10 respectively in our experiments.