Deep Video Harmonization With Color Mapping Consistency
Authors: Xinyuan Lu, Shengyuan Huang, Li Niu, Wenyan Cong, Liqing Zhang
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on our HYou Tube dataset prove the effectiveness of our proposed framework. |
| Researcher Affiliation | Academia | Mo E Key Lab of Artificial Intelligence, Department of Computer Science and Engineering Shanghai Jiaotong University, Shanghai, China {lxy9807, huangshengyuan, ustcnewly, plcwyam17320}@sjtu.edu.cn, zhang-lq@cs.sjtu.edu.cn |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our dataset and code are available at https://github.com/bcmi/Video Harmonization-Dataset-HYou Tube. |
| Open Datasets | Yes | In this work, we construct a new video harmonization dataset HYou Tube by adjusting the foreground of real videos to create synthetic composite videos. Our dataset and code are available at https://github.com/bcmi/Video Harmonization-Dataset-HYou Tube. |
| Dataset Splits | No | The paper states 'We split our dataset into 2558 video samples in the training set and 636 video samples in the test set', but it does not explicitly mention a separate validation set for hyperparameter tuning or early stopping. |
| Hardware Specification | Yes | We train our model on a single GTX 3090 GPU for 120 epochs... |
| Software Dependencies | No | The paper states 'We conduct all experiments using Pytorch' but does not specify the version number for Pytorch or any other software dependencies. |
| Experiment Setup | Yes | We set the number of neighboring frames T = 8 by default. The number of bins is set as B = 32, which is practically used in image processing. We train our model on a single GTX 3090 GPU for 120 epochs using Adam optimizer with β1 = 0.9, β2 = 0.999 and ϵ = 10 8. The initial learning rate is 10 3. The batch size is set to 32 for training process. We resize composite frames to 256 256 during training and testing. The random seed is set as 5. |