VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editing

• URL: http://arxiv.org/abs/2411.15260v1
• Date: Fri, 22 Nov 2024 10:04:05 GMT
• Title: VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editing
• Authors: Jiahao Hu, Tianxiong Zhong, Xuebo Wang, Boyuan Jiang, Xingye Tian, Fei Yang, Pengfei Wan, Di Zhang,
• Abstract summary: This paper introduces a dataset VIVID-10M and a baseline model VIVID. VIVID-10M is the first large-scale hybrid image-video local editing dataset. Our approach achieves state-of-the-art performance in video local editing, surpassing baseline methods in both automated metrics and user studies.
• Score: 13.006616304789878
• License:
• Abstract: Diffusion-based image editing models have made remarkable progress in recent years. However, achieving high-quality video editing remains a significant challenge. One major hurdle is the absence of open-source, large-scale video editing datasets based on real-world data, as constructing such datasets is both time-consuming and costly. Moreover, video data requires a significantly larger number of tokens for representation, which substantially increases the training costs for video editing models. Lastly, current video editing models offer limited interactivity, often making it difficult for users to express their editing requirements effectively in a single attempt. To address these challenges, this paper introduces a dataset VIVID-10M and a baseline model VIVID. VIVID-10M is the first large-scale hybrid image-video local editing dataset aimed at reducing data construction and model training costs, which comprises 9.7M samples that encompass a wide range of video editing tasks. VIVID is a Versatile and Interactive VIdeo local eDiting model trained on VIVID-10M, which supports entity addition, modification, and deletion. At its core, a keyframe-guided interactive video editing mechanism is proposed, enabling users to iteratively edit keyframes and propagate it to other frames, thereby reducing latency in achieving desired outcomes. Extensive experimental evaluations show that our approach achieves state-of-the-art performance in video local editing, surpassing baseline methods in both automated metrics and user studies. The VIVID-10M dataset and the VIVID editing model will be available at \url{https://inkosizhong.github.io/VIVID/}.

Related papers

• Video Instruction Tuning With Synthetic Data [84.64519990333406]
  We create a high-quality synthetic dataset specifically for video instruction-following, namely LLaVA-Video-178K. This dataset includes key tasks such as detailed captioning, open-ended question-answering (QA), and multiple-choice QA. By training on this dataset, in combination with existing visual instruction tuning data, we introduce LLaVA-Video, a new video LMM.
  arXiv  Detail & Related papers  (2024-10-03T17:36:49Z)
• Temporally Consistent Object Editing in Videos using Extended Attention [9.605596668263173]
  We propose a method to edit videos using a pre-trained inpainting image diffusion model. We ensure that the edited information will be consistent across all the video frames.
  arXiv  Detail & Related papers  (2024-06-01T02:31:16Z)
• AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks [41.640692114423544]
  We introduce AnyV2V, a novel tuning-free paradigm designed to simplify video editing. AnyV2V can leverage any existing image editing tools to support an extensive array of video editing tasks. Our evaluation shows that AnyV2V achieved CLIP-scores comparable to other baseline methods.
  arXiv  Detail & Related papers  (2024-03-21T15:15:00Z)
• EffiVED:Efficient Video Editing via Text-instruction Diffusion Models [9.287394166165424]
  We introduce EffiVED, an efficient diffusion-based model that supports instruction-guided video editing. We transform vast image editing datasets and open-world videos into a high-quality dataset for training EffiVED.
  arXiv  Detail & Related papers  (2024-03-18T08:42:08Z)
• Neural Video Fields Editing [56.558490998753456]
  NVEdit is a text-driven video editing framework designed to mitigate memory overhead and improve consistency. We construct a neural video field, powered by tri-plane and sparse grid, to enable encoding long videos with hundreds of frames. Next, we update the video field through off-the-shelf Text-to-Image (T2I) models to text-driven editing effects.
  arXiv  Detail & Related papers  (2023-12-12T14:48:48Z)
• VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models [96.55004961251889]
  Video Instruction Diffusion (VIDiff) is a unified foundation model designed for a wide range of video tasks. Our model can edit and translate the desired results within seconds based on user instructions. We provide convincing generative results for diverse input videos and written instructions, both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2023-11-30T18:59:52Z)
• Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models [65.268245109828]
  Ground-A-Video is a video-to-video translation framework for multi-attribute video editing. It attains temporally consistent editing of input videos in a training-free manner. Experiments and applications demonstrate that Ground-A-Video's zero-shot capacity outperforms other baseline methods in terms of edit-accuracy and frame consistency.
  arXiv  Detail & Related papers  (2023-10-02T11:28:37Z)
• EVE: Efficient zero-shot text-based Video Editing with Depth Map Guidance and Temporal Consistency Constraints [20.1875350156484]
  Current video editing tasks mainly suffer from the dilemma between the high fine-tuning cost and the limited generation capacity. We propose EVE, a robust and efficient zero-shot video editing method. Under the guidance of depth maps and temporal consistency constraints, EVE derives satisfactory video editing results with an affordable computational and time cost.
  arXiv  Detail & Related papers  (2023-08-21T11:36:46Z)
• Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models [68.31777975873742]
  Recent attempts at video editing require significant text-to-video data and computation resources for training. We propose vid2vid-zero, a simple yet effective method for zero-shot video editing. Experiments and analyses show promising results in editing attributes, subjects, places, etc., in real-world videos.
  arXiv  Detail & Related papers  (2023-03-30T17:59:25Z)
• Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [80.7397409377659]
  We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captioning datasets. Our model is flexible and can be trained on both image and video text datasets, either independently or in conjunction. We show that this approach yields state-of-the-art results on standard downstream video-retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-04-01T17:48:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.