TTVFI: Learning Trajectory-Aware Transformer for Video Frame
Interpolation
- URL: http://arxiv.org/abs/2207.09048v1
- Date: Tue, 19 Jul 2022 03:37:49 GMT
- Title: TTVFI: Learning Trajectory-Aware Transformer for Video Frame
Interpolation
- Authors: Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian
- Abstract summary: Video frame (VFI) aims to synthesize an intermediate frame between two consecutive frames.
We propose a novel Trajectory-aware Transformer for Video Frame Interpolation (TTVFI)
Our method outperforms other state-of-the-art methods in four widely-used VFI benchmarks.
- Score: 50.49396123016185
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Video frame interpolation (VFI) aims to synthesize an intermediate frame
between two consecutive frames. State-of-the-art approaches usually adopt a
two-step solution, which includes 1) generating locally-warped pixels by
flow-based motion estimations, 2) blending the warped pixels to form a full
frame through deep neural synthesis networks. However, due to the inconsistent
warping from the two consecutive frames, the warped features for new frames are
usually not aligned, which leads to distorted and blurred frames, especially
when large and complex motions occur. To solve this issue, in this paper we
propose a novel Trajectory-aware Transformer for Video Frame Interpolation
(TTVFI). In particular, we formulate the warped features with inconsistent
motions as query tokens, and formulate relevant regions in a motion trajectory
from two original consecutive frames into keys and values. Self-attention is
learned on relevant tokens along the trajectory to blend the pristine features
into intermediate frames through end-to-end training. Experimental results
demonstrate that our method outperforms other state-of-the-art methods in four
widely-used VFI benchmarks. Both code and pre-trained models will be released
soon.
Related papers
- Framer: Interactive Frame Interpolation [73.06734414930227]
Framer targets producing smoothly transitioning frames between two images as per user creativity.
Our approach supports customizing the transition process by tailoring the trajectory of some selected keypoints.
It is noteworthy that our system also offers an "autopilot" mode, where we introduce a module to estimate the keypoints and the trajectory automatically.
arXiv Detail & Related papers (2024-10-24T17:59:51Z) - ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler [53.98558445900626]
Current image-to-video diffusion models, while powerful in generating videos from a single frame, need adaptation for two-frame conditioned generation.
We introduce a novel, bidirectional sampling strategy to address these off-manifold issues without requiring extensive re-noising or fine-tuning.
Our method employs sequential sampling along both forward and backward paths, conditioned on the start and end frames, respectively, ensuring more coherent and on-manifold generation of intermediate frames.
arXiv Detail & Related papers (2024-10-08T03:01:54Z) - E-VFIA : Event-Based Video Frame Interpolation with Attention [8.93294761619288]
We propose an event-based video frame with attention (E-VFIA) as a lightweight kernel-based method.
E-VFIA fuses event information with standard video frames by deformable convolutions to generate high quality interpolated frames.
The proposed method represents events with high temporal resolution and uses a multi-head self-attention mechanism to better encode event-based information.
arXiv Detail & Related papers (2022-09-19T21:40:32Z) - Video Frame Interpolation without Temporal Priors [91.04877640089053]
Video frame aims to synthesize non-exist intermediate frames in a video sequence.
The temporal priors of videos, i.e. frames per second (FPS) and frame exposure time, may vary from different camera sensors.
We devise a novel optical flow refinement strategy for better synthesizing results.
arXiv Detail & Related papers (2021-12-02T12:13:56Z) - Asymmetric Bilateral Motion Estimation for Video Frame Interpolation [50.44508853885882]
We propose a novel video frame algorithm based on asymmetric bilateral motion estimation (ABME)
We predict symmetric bilateral motion fields to interpolate an anchor frame.
We estimate asymmetric bilateral motions fields from the anchor frame to the input frames.
Third, we use the asymmetric fields to warp the input frames backward and reconstruct the intermediate frame.
arXiv Detail & Related papers (2021-08-15T21:11:35Z) - ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and
Interpolation [38.52446103418748]
We introduce a novel architecture, Adaptive Latent Attention Network (ALANET), which synthesizes sharp high frame-rate videos.
We employ combination of self-attention and cross-attention module between consecutive frames in the latent space to generate optimized representation for each frame.
Our method performs favorably against various state-of-the-art approaches, even though we tackle a much more difficult problem.
arXiv Detail & Related papers (2020-08-31T21:11:53Z) - Deep Sketch-guided Cartoon Video Inbetweening [24.00033622396297]
We propose a framework to produce cartoon videos by fetching the color information from two inputs while following the animated motion guided by a user sketch.
By explicitly considering the correspondence between frames and the sketch, we can achieve higher quality results than other image synthesis methods.
arXiv Detail & Related papers (2020-08-10T14:22:04Z) - All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced
Motion Modeling [52.425236515695914]
State-of-the-art methods are iterative solutions interpolating one frame at the time.
This work introduces a true multi-frame interpolator.
It utilizes a pyramidal style network in the temporal domain to complete the multi-frame task in one-shot.
arXiv Detail & Related papers (2020-07-23T02:34:39Z)
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.