paper-with-me

홈 › Papers

RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives

2024-05-28 · Jaehong Yoon, Shoubin Yu, Mohit Bansal

Recent video generative models primarily rely on carefully written text prompts for specific tasks, like inpainting or style editing. They require labor-intensive textual descriptions for input videos, hindering their flexibility to adapt personal/raw videos to user specifications. This paper proposes RACCooN, a versatile and user-friendly video-to-paragraph-to-video generative framework that supports multiple video editing capabilities such as removal, addition, and modification, through a unified pipeline. RACCooN consists of two principal stages: Video-to-Paragraph (V2P) and Paragraph-to-Video (P2V). In the V2P stage, we automatically describe video scenes in well-structured natural language, capturing both the holistic context and focused object details. Subsequently, in the P2V stage, users can optionally refine these descriptions to guide the video diffusion model, enabling various modifications to the input video, such as removing, changing subjects, and/or adding new objects. The proposed approach stands out from other methods through several significant contributions: (1) RACCooN suggests a multi-granular spatiotemporal pooling strategy to generate well-structured video descriptions, capturing both the broad context and object details without requiring complex human annotations, simplifying precise video content editing based on text for users. (2) Our video generative model incorporates auto-generated narratives or instructions to enhance the quality and accuracy of the generated content. (3) RACCooN also plans to imagine new objects in a given video, so users simply prompt the model to receive a detailed video editing plan for complex video editing. The proposed framework demonstrates impressive versatile capabilities in video-to-paragraph generation, video content editing, and can be incorporated into other SoTA video generative models for further enhancement.

📄 PDF Abstract BibTeX arXiv:2405.18406

Code (2)

jaehong31/raccoon 공식 구현 pytorch
adymaharana/adapt-inf pytorch

Tasks

AttributeVideo Editing

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation

2025-03-18 · Shoubin Yu, Difan Liu, Ziqiao Ma, Yicong Hong 외

Recent video diffusion models have enhanced video editing, but it remains challenging to handle instructional editing and diverse tasks (e.g., adding, removing, changing) within a unified framework. In this paper, we int…

Reasoning SegmentationVideo Editing

Region-Constraint In-Context Generation for Instructional Video Editing

2025-12-19 · Zhongwei Zhang, Fuchen Long, Wei Li, Zhaofan Qiu 외 arxiv

The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such in-context learning for instruction-bas…

Image Editing

InstructVEdit: A Holistic Approach for Instructional Video Editing

2025-03-22 · Chi Zhang, Chengjian Feng, Feng Yan, Qiming Zhang 외

Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data b…

Video Editing

SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing

2024-05-07 · Yuying Ge, Sijie Zhao, Chen Li, Yixiao Ge 외

In this technical report, we introduce SEED-Data-Edit: a unique hybrid dataset for instruction-guided image editing, which aims to facilitate image manipulation using open-form language. SEED-Data-Edit is composed of thr…

Image ManipulationLanguage ModelingLanguage ModellingLarge Language Model+1

RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles

2025-01-20 · Jonathan Lin, Aditya Joshi, Hye-Young Paik, Tri Dung Doung 외

Geocoding involves automatic extraction of location coordinates of incidents reported in news articles, and can be used for epidemic intelligence or disaster management. This paper introduces Retrieval-Augmented Coordina…

ArticlesManagementRAGRetrieval+1