Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]
Drafting and Revision: Advancing High-Fidelity Video Inpainting
Authors: Zhiliang Wu, Kun Li, Hehe Fan, Yi Yang
IJCAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Experiments 4.1 Experimental Setting Datasets. Following previous works [Ren et al., 2022; Zhou et al., 2023; Wu et al., 2024], two most commonly used datasets (Youtube-vos [Xu et al., 2018] and DAVIS [Perazzi et al., 2016]) are considered to verify the effectiveness of our method. Baselines and Evaluation Metrics. We select nine recently video inpainting methods as our baselines... Furthermore, PSNR [Haotian et al., 2019], SSIM [Lin et al., 2021], LPIPS [Zhang et al., 2018], and Ewarp [Lai et al., 2018] are used to evaluate inpainting quality. 4.2 Experimental Results and Analysis Quantitative Results. Tab. 1 shows quantitative results on Youtube-vos and DAVIS datasets under 256 256 resolution. Qualitative Results. In Fig. 4, we visually compare the qualitative results of our method with five baselines... 4.4 Ablation Study Drafting Network. To demonstrate the effectiveness of Drafting Network, we replaced the Drafting Network in our framework with two baseline models (STTN [Zeng et al., 2020], and E2FGVI [Li et al., 2022]) and compared their results with our full model. |
| Researcher Affiliation | Academia | Zhiliang Wu , Kun Li , Hehe Fan and Yi Yang Re LER, CCAI, Zhejiang University, China |
| Pseudocode | No | The paper describes the proposed method, DRCN, through network architecture descriptions and diagrams (Figure 2, Figure 3), and mathematical formulations. It does not contain any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain an explicit statement about releasing source code for the described methodology, nor does it provide a direct link to a code repository. |
| Open Datasets | Yes | Datasets. Following previous works [Ren et al., 2022; Zhou et al., 2023; Wu et al., 2024], two most commonly used datasets (Youtube-vos [Xu et al., 2018] and DAVIS [Perazzi et al., 2016]) are considered to verify the effectiveness of our method. |
| Dataset Splits | Yes | The Youtube-vos [Xu et al., 2018] dataset contains 4453 videos with various scenes, and is split into three parts containing 3471, 474 and 508 videos for training, validation and testing, respectively. As for the DAVIS [Perazzi et al., 2016] dataset, it contains 150 high-quality videos of challenging motion-blur and appearance motions. Consistent with existing studies [Zhou et al., 2023; Yu et al., 2023; Zhang et al., 2024; Wu et al., 2024], 60 videos are used for training and 90 videos are utilized for testing. |
| Hardware Specification | Yes | Tab. 2 shows the quantitative results at three different resolutions on Youtube-vos [Xu et al., 2018] dataset, which were tested under a RTX 2080 Ti GPU. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies or libraries used in the implementation or experimentation. |
| Experiment Setup | No | The paper describes the overall network architecture and components, and details of the loss functions. However, it does not explicitly provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) for training their model, DRCN. |