Learning to Animate Images from A Few Videos to Portray Delicate Human Actions

• URL: http://arxiv.org/abs/2503.00276v2
• Date: Mon, 10 Mar 2025 08:32:16 GMT
• Title: Learning to Animate Images from A Few Videos to Portray Delicate Human Actions
• Authors: Haoxin Li, Yingchen Yu, Qilong Wu, Hanwang Zhang, Song Bai, Boyang Li,
• Abstract summary: Video generative models still struggle to animate static images into videos that portray delicate human actions.<n>In this paper, we explore the task of learning to animate images to portray delicate human actions using a small number of videos.<n>We propose FLASH, which learns generalizable motion patterns by forcing the model to reconstruct a video using the motion features and cross-frame correspondences of another video.
• Score: 80.61838364885482
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite recent progress, video generative models still struggle to animate static images into videos that portray delicate human actions, particularly when handling uncommon or novel actions whose training data are limited. In this paper, we explore the task of learning to animate images to portray delicate human actions using a small number of videos -- 16 or fewer -- which is highly valuable for real-world applications like video and movie production. Learning generalizable motion patterns that smoothly transition from user-provided reference images in a few-shot setting is highly challenging. We propose FLASH (Few-shot Learning to Animate and Steer Humans), which learns generalizable motion patterns by forcing the model to reconstruct a video using the motion features and cross-frame correspondences of another video with the same motion but different appearance. This encourages transferable motion learning and mitigates overfitting to limited training data. Additionally, FLASH extends the decoder with additional layers to propagate details from the reference image to generated frames, improving transition smoothness. Human judges overwhelmingly favor FLASH, with 65.78\% of 488 responses prefer FLASH over baselines. We strongly recommend watching the videos in the website: https://lihaoxin05.github.io/human_action_animation/, as motion artifacts are hard to notice from images.

Related papers

• AnimateAnywhere: Rouse the Background in Human Image Animation [50.737139810172465]
  AnimateAnywhere is a framework to rousing the background in human image animation without requirements on camera trajectories. We introduce a background motion learner (BML) to learn background motions from human pose sequences. Experiments demonstrate that our AnimateAnywhere effectively learns the background motion from human pose sequences.
  arXiv  Detail & Related papers  (2025-04-28T14:35:01Z)
• Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics [67.97235923372035]
  We present Puppet-Master, an interactive video generative model that can serve as a motion prior for part-level dynamics. At test time, given a single image and a sparse set of motion trajectories, Puppet-Master can synthesize a video depicting realistic part-level motion faithful to the given drag interactions.
  arXiv  Detail & Related papers  (2024-08-08T17:59:38Z)
• Controllable Longer Image Animation with Diffusion Models [12.565739255499594]
  We introduce an open-domain controllable image animation method using motion priors with video diffusion models. Our method achieves precise control over the direction and speed of motion in the movable region by extracting the motion field information from videos. We propose an efficient long-duration video generation method based on noise reschedule specifically tailored for image animation tasks.
  arXiv  Detail & Related papers  (2024-05-27T16:08:00Z)
• AniClipart: Clipart Animation with Text-to-Video Priors [28.76809141136148]
  We introduce AniClipart, a computational system that converts static animations into high-quality animations guided by text-to-video prior.<n>By differentiable As-Rigid-As-Possible (ARAP) shape deformation and differentiable rendering, AniClipart can be end-to-end optimized while maintaining rigidity.
  arXiv  Detail & Related papers  (2024-04-18T17:24:28Z)
• 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)
• 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)
• Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation [27.700371215886683]
  diffusion models have become the mainstream in visual generation research, owing to their robust generative capabilities. In this paper, we propose a novel framework tailored for character animation. By expanding the training data, our approach can animate arbitrary characters, yielding superior results in character animation compared to other image-to-video methods.
  arXiv  Detail & Related papers  (2023-11-28T12:27:15Z)
• MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model [74.84435399451573]
  This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion. We introduce MagicAnimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity.
  arXiv  Detail & Related papers  (2023-11-27T18:32:31Z)
• Breathing Life Into Sketches Using Text-to-Video Priors [101.8236605955899]
  A sketch is one of the most intuitive and versatile tools humans use to convey their ideas visually. In this work, we present a method that automatically adds motion to a single-subject sketch. The output is a short animation provided in vector representation, which can be easily edited.
  arXiv  Detail & Related papers  (2023-11-21T18:09:30Z)
• AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance [13.416296247896042]
  We introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and motion strength guidance, enabling precise control of the movable area and its motion speed. We validate the effectiveness of our method through rigorous experiments on an open-domain dataset.
  arXiv  Detail & Related papers  (2023-11-21T03:47:54Z)
• DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors [63.43133768897087]
  We propose a method to convert open-domain images into animated videos. The key idea is to utilize the motion prior to text-to-video diffusion models by incorporating the image into the generative process as guidance. Our proposed method can produce visually convincing and more logical & natural motions, as well as higher conformity to the input image.
  arXiv  Detail & Related papers  (2023-10-18T14:42:16Z)
• SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches [0.9645196221785693]
  2D animation is a common factor in game development, used for characters, effects and background art. Automated animation approaches exist, but are designed without animators in mind. We propose a problem formulation that adheres more closely to the standard workflow of animation.
  arXiv  Detail & Related papers  (2022-09-01T02:43:19Z)
• Learning Fine-Grained Motion Embedding for Landscape Animation [140.57889994591494]
  We propose a model named FGLA to generate high-quality and realistic videos by learning Fine-Grained motion embedding. To train and evaluate on diverse time-lapse videos, we build the largest high-resolution Time-lapse video dataset with Diverse scenes. Our method achieves relative improvements by 19% on LIPIS and 5.6% on FVD compared with state-of-the-art methods on our dataset.
  arXiv  Detail & Related papers  (2021-09-06T02:47:11Z)
• First Order Motion Model for Image Animation [90.712718329677]
  Image animation consists of generating a video sequence so that an object in a source image is animated according to the motion of a driving video. Our framework addresses this problem without using any annotation or prior information about the specific object to animate.
  arXiv  Detail & Related papers  (2020-02-29T07:08:56Z)

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.