2026-04-17T20:36:01Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4102642025-07-22T22:49:42Zcom_2072_1033col_2072_452951

Temporally-coherent video cartoonization Rayo Hernandez, Gustavo Enrique Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors Tous Liesa, Rubén Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial Video recording Artificial intelligence Video cartoonization video-to-video translation diffusion model Stable Diffusion ControlNet EbSynth Vídeo Intel·ligència artificial The automatic transformation of short background videos from real scenarios into others with a visually pleasing style, like those used in cartoons, holds application in various domains. These include animated films, video games, advertisements, and many other areas that involve visual content creation. A method or tool that can perform this task, would inspire, facilitate, and streamline the work of artists and people who produce this type of content. This thesis proposes a method that integrates multiple components to translate short background videos into others that contain a particular style. We employ Stable Diffusion, a text-to-image diffusion model, along with other technologies like ControlNet to translate keyframes from the source video, ensuring content preservation. The style of the transformed keyframes is propagated to the rest of the frames using EbSynth to make the process faster and maintain the temporal coherence. We quantitatively assess content preservation and temporal coherence using CLIP-based metrics over a new dataset of videos translated into three distinct styles. The implementation of our method is publicly available at https://github.com/gustavorayo/video-to-cartoon 2024-01-25 Master thesis https://hdl.handle.net/2117/410264 183260 eng Open Access application/pdf Universitat Politècnica de Catalunya