{"type":"ScholarlyArticle","title":"Drafting and Revision: Advancing High-Fidelity Video Inpainting","authors":[{"name":"Zhiliang Wu","slug":"zhiliang-wu","given":"Zhiliang","family":"Wu","affiliation":""},{"name":"Kun Li","slug":"kun-li","given":"Kun","family":"Li","affiliation":""},{"name":"Hehe Fan","slug":"hehe-fan","given":"Hehe","family":"Fan","affiliation":""},{"name":"Yi Yang","slug":"yi-yang","given":"Yi","family":"Yang","affiliation":""}],"abstract":"Video inpainting aims to fill the missing regions in video with spatial-temporally coherent contents. Existing methods usually treat the missing contents as a whole and adopt a hybrid objective containing a reconstruction loss and an adversarial loss to train the model. However, these two kinds of loss focus on contents at different frequencies, simply combining them may cause inter-frequency conflicts, leading the trained model to generate compromised results. Inspired by the common corrupted painting restoration process of “drawing a draft first and then revising the details later”, this paper proposes a Drafting-and-Revision Completion Network (DRCN) for video inpainting. Specifically, we first design a Drafting Network that utilizes the temporal information to complete the low-frequency semantic structure at low resolution. Then, a Revision Network is developed to hallucinate high-frequency details at high resolution by using the output of Drafting Network. In this way, adversarial loss and reconstruction loss can be applied to high-frequency and low-frequency respectively, effectively mitigating inter-frequency conflicts. Furthermore, Revision Network can be stacked in a pyramid manner to generate higher resolution details, which provide a feasible solution for high-resolution video inpainting. Experiments show that DRCN achieves improvements of 7.43% and 12.64% in E_warp and LPIPS, and can handle higher resolution videos on limited GPU memory.","doi":"10.24963/ijcai.2025/230","url":"https://ijcai.org/proceedings/2025/230","pdf":"https://ijcai.org/proceedings/2025/0230.pdf","markdown":"https://ijcai.org/proceedings/2025/230.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/230","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":230,"pages":{"first":2063,"last":2071},"keywords":["Computer Vision: CV: Image and video synthesis and generation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}