paper-with-me

Papers

Disentangling Content and Motion for Text-Based Neural Video Manipulation

2022-11-05 · Levent Karacan, Tolga Kerimoğlu, İsmail İnan, Tolga Birdal, Erkut Erdem, Aykut Erdem

Giving machines the ability to imagine possible new objects or scenes from linguistic descriptions and produce their realistic renderings is arguably one of the most challenging problems in computer vision. Recent advances in deep generative models have led to new approaches that give promising results towards this goal. In this paper, we introduce a new method called DiCoMoGAN for manipulating videos with natural language, aiming to perform local and semantic edits on a video clip to alter the appearances of an object of interest. Our GAN architecture allows for better utilization of multiple observations by disentangling content and motion to enable controllable semantic edits. To this end, we introduce two tightly coupled networks: (i) a representation network for constructing a concise understanding of motion dynamics and temporally invariant content, and (ii) a translation network that exploits the extracted latent content representation to actuate the manipulation according to the target description. Our qualitative and quantitative evaluations demonstrate that DiCoMoGAN significantly outperforms existing frame-based methods, producing temporally coherent and semantically more meaningful results.

📄 PDF Abstract BibTeX arXiv:2211.02980

Code (1)

leventkaracan/dicomogan 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Decouple Content and Motion for Conditional Image-to-Video Generation

2023-11-24 · Cuifeng Shen, Yulu Gan, Chen Chen, Xiongwei Zhu 외

The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i.e., one image and text.The previous cI2V generation methods conventionally perform in RGB pi…

Image to Video GenerationVideo Generation

Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization

2026-06-25 · Xuancheng Xu, Gengyun Jia, Bing-Kun Bao arxiv

Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos. While significant strides have been made in image stylization and video motion …

Text-to-Video Generation

Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video

2025-09-10 · Xiao Li, Qi Chen, Xiulian Peng, Kai Yu 외 arxiv

We propose a novel and general framework to disentangle video data into its dynamic motion and static content components. Our proposed method is a self-supervised pipeline with less assumptions and inductive biases than …

Self-Supervised LearningRepresentation Learning

MagicEdit: High-Fidelity and Temporally Coherent Video Editing

2023-08-28 · Jun Hao Liew, Hanshu Yan, Jianfeng Zhang, Zhongcong Xu 외

In this report, we present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task. We found that high-fidelity and temporally coherent video-to-video translation can be achieved by …

TranslationVideo Editing

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

2023-04-12 · ICCV 2023 1 · Moayed Haji Ali, Andrew Bond, Tolga Birdal, Duygu Ceylan 외

We propose $\textbf{VidStyleODE}$, a spatiotemporally continuous disentangled $\textbf{Vid}$eo representation based upon $\textbf{Style}$GAN and Neural-$\textbf{ODE}$s. Effective traversal of the latent space learned by …

Image AnimationVideo EditingVideo Generation