Pix2Gif: Motion-Guided Diffusion for GIF Generation

• URL: http://arxiv.org/abs/2403.04634v2
• Date: Fri, 8 Mar 2024 18:28:28 GMT
• Title: Pix2Gif: Motion-Guided Diffusion for GIF Generation
• Authors: Hitesh Kandala, Jianfeng Gao, Jianwei Yang
• Abstract summary: We present Pix2Gif, a motion-guided diffusion model for image-to-GIF (video) generation. We propose a new motion-guided warping module to spatially transform the features of the source image conditioned on the two types of prompts. In preparation for the model training, we meticulously curated data by extracting coherent image frames from the TGIF video-caption dataset.
• Score: 70.64240654310754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Pix2Gif, a motion-guided diffusion model for image-to-GIF (video) generation. We tackle this problem differently by formulating the task as an image translation problem steered by text and motion magnitude prompts, as shown in teaser fig. To ensure that the model adheres to motion guidance, we propose a new motion-guided warping module to spatially transform the features of the source image conditioned on the two types of prompts. Furthermore, we introduce a perceptual loss to ensure the transformed feature map remains within the same space as the target image, ensuring content consistency and coherence. In preparation for the model training, we meticulously curated data by extracting coherent image frames from the TGIF video-caption dataset, which provides rich information about the temporal changes of subjects. After pretraining, we apply our model in a zero-shot manner to a number of video datasets. Extensive qualitative and quantitative experiments demonstrate the effectiveness of our model -- it not only captures the semantic prompt from text but also the spatial ones from motion guidance. We train all our models using a single node of 16xV100 GPUs. Code, dataset and models are made public at: https://hiteshk03.github.io/Pix2Gif/.

Related papers

• MotionFix: Text-Driven 3D Human Motion Editing [52.11745508960547]
  Key challenges include the scarcity of training data and the need to design a model that accurately edits the source motion. We propose a methodology to semi-automatically collect a dataset of triplets comprising (i) a source motion, (ii) a target motion, and (iii) an edit text. Access to this data allows us to train a conditional diffusion model, TMED, that takes both the source motion and the edit text as input.
  arXiv  Detail & Related papers  (2024-08-01T16:58:50Z)
• StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation [117.13475564834458]
  We propose a new way of self-attention calculation, termed Consistent Self-Attention. To extend our method to long-range video generation, we introduce a novel semantic space temporal motion prediction module. By merging these two novel components, our framework, referred to as StoryDiffusion, can describe a text-based story with consistent images or videos.
  arXiv  Detail & Related papers  (2024-05-02T16:25:16Z)
• LoopAnimate: Loopable Salient Object Animation [19.761865029125524]
  LoopAnimate is a novel method for generating videos with consistent start and end frames. It achieves state-of-the-art performance in both objective metrics, such as fidelity and temporal consistency, and subjective evaluation results.
  arXiv  Detail & Related papers  (2024-04-14T07:36:18Z)
• Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models [48.56724784226513]
  We propose Customize-A-Video that models the motion from a single reference video and adapts it to new subjects and scenes with both spatial and temporal varieties. The proposed modules are trained in a staged pipeline and inferred in a plug-and-play fashion, enabling easy extensions to various downstream tasks.
  arXiv  Detail & Related papers  (2024-02-22T18:38:48Z)
• LatentMan: Generating Consistent Animated Characters using Image Diffusion Models [44.18315132571804]
  We propose a zero-shot approach for generating consistent videos of animated characters based on Text-to-Image (T2I) diffusion models. Our proposed approach outperforms existing zero-shot T2V approaches in generating videos of animated characters in terms of pixel-wise consistency and user preference.
  arXiv  Detail & Related papers  (2023-12-12T10:07:37Z)
• AnimateZero: Video Diffusion Models are Zero-Shot Image Animators [63.938509879469024]
  We propose AnimateZero to unveil the pre-trained text-to-video diffusion model, i.e., AnimateDiff. For appearance control, we borrow intermediate latents and their features from the text-to-image (T2I) generation. For temporal control, we replace the global temporal attention of the original T2V model with our proposed positional-corrected window attention.
  arXiv  Detail & Related papers  (2023-12-06T13:39:35Z)
• DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance [69.0740091741732]
  We propose a high-fidelity image-to-video generation method by devising a frame retention branch based on a pre-trained video diffusion model, named DreamVideo. Our model has a powerful image retention ability and delivers the best results in UCF101 compared to other image-to-video models to our best knowledge.
  arXiv  Detail & Related papers  (2023-12-05T03:16:31Z)
• VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models [58.93124686141781]
  Video Motion Customization (VMC) is a novel one-shot tuning approach crafted to adapt temporal attention layers within video diffusion models. Our approach introduces a novel motion distillation objective using residual vectors between consecutive frames as a motion reference. We validate our method against state-of-the-art video generative models across diverse real-world motions and contexts.
  arXiv  Detail & Related papers  (2023-12-01T06:50:11Z)
• Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding [47.97650346560239]
  We propose Spatial-Temporal Auxiliary Network with Mutual-guided alignment module (Mug-STAN) to extend image-text model to diverse video tasks and video-text data. Mug-STAN significantly improves adaptation of language-image pretrained models such as CLIP and CoCa at both video-text post-pretraining and finetuning stages.
  arXiv  Detail & Related papers  (2023-11-25T17:01:38Z)
• Vision Transformer Based Model for Describing a Set of Images as a Story [26.717033245063092]
  We propose a novel Vision Transformer Based Model for describing a set of images as a story. The proposed method extracts the distinct features of the input images using a Vision Transformer (ViT) The performance of our proposed model is evaluated using the Visual Story-Telling dataset (VIST)
  arXiv  Detail & Related papers  (2022-10-06T09:01:50Z)

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.