GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion Estimates

• URL: http://arxiv.org/abs/2210.13769v2
• Date: Wed, 26 Oct 2022 05:36:53 GMT
• Title: GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion Estimates
• Authors: Jerin Geo James (1), Devansh Jain (1), Ajit Rajwade (1) ((1) Indian Institute of Technology Bombay)
• Abstract summary: Videos shot by laymen using hand-held cameras contain undesirable shaky motion. Estimating the global motion between successive frames is central to many video stabilization techniques. We introduce a more general representation scheme, which adapts any existing optical flow network to ignore the moving objects.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Videos shot by laymen using hand-held cameras contain undesirable shaky motion. Estimating the global motion between successive frames, in a manner not influenced by moving objects, is central to many video stabilization techniques, but poses significant challenges. A large body of work uses 2D affine transformations or homography for the global motion. However, in this work, we introduce a more general representation scheme, which adapts any existing optical flow network to ignore the moving objects and obtain a spatially smooth approximation of the global motion between video frames. We achieve this by a knowledge distillation approach, where we first introduce a low pass filter module into the optical flow network to constrain the predicted optical flow to be spatially smooth. This becomes our student network, named as \textsc{GlobalFlowNet}. Then, using the original optical flow network as the teacher network, we train the student network using a robust loss function. Given a trained \textsc{GlobalFlowNet}, we stabilize videos using a two stage process. In the first stage, we correct the instability in affine parameters using a quadratic programming approach constrained by a user-specified cropping limit to control loss of field of view. In the second stage, we stabilize the video further by smoothing global motion parameters, expressed using a small number of discrete cosine transform coefficients. In extensive experiments on a variety of different videos, our technique outperforms state of the art techniques in terms of subjective quality and different quantitative measures of video stability. The source code is publicly available at \href{https://github.com/GlobalFlowNet/GlobalFlowNet}{https://github.com/GlobalFlowNet/GlobalFlowNet}

Related papers

• AnimateAnything: Consistent and Controllable Animation for Video Generation [24.576022028967195]
  We present a unified controllable video generation approach AnimateAnything. It facilitates precise and consistent video manipulation across various conditions. Experiments demonstrate that our method outperforms the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-11-16T16:36:49Z)
• ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video [26.01796507893086]
  This paper proposes a 3D motion perception method called ScaleFlow++ that is easy to generalize. With just a pair of RGB images, ScaleFlow++ can robustly estimate optical flow and motion-in-depth (MID) On KITTI, ScaleFlow++ achieved the best monocular scene flow estimation performance, reducing SF-all from 6.21 to 5.79.
  arXiv  Detail & Related papers  (2024-09-16T11:59:27Z)
• 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)
• ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video [15.629496237910999]
  This paper proposes a 3D motion perception method called ScaleFlow++ that is easy to generalize. With just a pair of RGB images, ScaleFlow++ can robustly estimate optical flow and motion-in-depth (MID) On KITTI, ScaleFlow++ achieved the best monocular scene flow estimation performance, reducing SF-all from 6.21 to 5.79.
  arXiv  Detail & Related papers  (2024-07-13T07:58:48Z)
• Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring [71.60457491155451]
  Eliminating image blur produced by various kinds of motion has been a challenging problem. We propose a novel real-world deblurring filtering model called the Motion-adaptive Separable Collaborative Filter. Our method provides an effective solution for real-world motion blur removal and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-04-19T19:44:24Z)
• Fast Full-frame Video Stabilization with Iterative Optimization [21.962533235492625]
  We propose an iterative optimization-based learning approach using synthetic datasets for video stabilization. We develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. We take a divide-and-conquer approach and propose a novel multiframe fusion strategy to render full-frame stabilized views.
  arXiv  Detail & Related papers  (2023-07-24T13:24:19Z)
• Tracking Everything Everywhere All at Once [111.00807055441028]
  We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. We propose a complete and globally consistent motion representation, dubbed OmniMotion. Our approach outperforms prior state-of-the-art methods by a large margin both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2023-06-08T17:59:29Z)
• Minimum Latency Deep Online Video Stabilization [77.68990069996939]
  We present a novel camera path optimization framework for the task of online video stabilization. In this work, we adopt recent off-the-shelf high-quality deep motion models for motion estimation to recover the camera trajectory. Our approach significantly outperforms state-of-the-art online methods both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-12-05T07:37:32Z)
• Unsupervised Video Interpolation by Learning Multilayered 2.5D Motion Fields [75.81417944207806]
  This paper presents a self-supervised approach to video frame learning that requires only a single video. We parameterize the video motions by solving an ordinary differentiable equation (ODE) defined on a time-varying motion field. This implicit neural representation learns the video as a space-time continuum, allowing frame-time continuum at any temporal resolution.
  arXiv  Detail & Related papers  (2022-04-21T06:17:05Z)
• FILM: Frame Interpolation for Large Motion [20.04001872133824]
  We present a frame algorithm that synthesizes multiple intermediate frames from two input images with large in-between motion. Our approach outperforms state-of-the-art methods on the Xiph large motion benchmark.
  arXiv  Detail & Related papers  (2022-02-10T08:48:18Z)
• Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer [67.36785832888614]
  This paper proposes to learn a lightweight video style transfer network via knowledge distillation paradigm. We adopt two teacher networks, one of which takes optical flow during inference while the other does not. The output difference between these two teacher networks highlights the improvements made by optical flow, which is then adopted to distill the target student network.
  arXiv  Detail & Related papers  (2020-07-10T03:00:33Z)

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.