BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation

• URL: http://arxiv.org/abs/2007.12622v1
• Date: Fri, 17 Jul 2020 09:07:51 GMT
• Title: BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
• Authors: Junheum Park, Keunsoo Ko, Chul Lee, Chang-Su Kim
• Abstract summary: Video increases the temporal resolution of a video sequence by synthesizing intermediate frames between two consecutive frames. We propose a novel deep-learning-based video algorithm based on bilateral motion estimation. Experimental results show that the proposed algorithm outperforms the state-of-the-art video algorithms on several benchmark datasets.
• Score: 42.40306256282872
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video interpolation increases the temporal resolution of a video sequence by synthesizing intermediate frames between two consecutive frames. We propose a novel deep-learning-based video interpolation algorithm based on bilateral motion estimation. First, we develop the bilateral motion network with the bilateral cost volume to estimate bilateral motions accurately. Then, we approximate bi-directional motions to predict a different kind of bilateral motions. We then warp the two input frames using the estimated bilateral motions. Next, we develop the dynamic filter generation network to yield dynamic blending filters. Finally, we combine the warped frames using the dynamic blending filters to generate intermediate frames. Experimental results show that the proposed algorithm outperforms the state-of-the-art video interpolation algorithms on several benchmark datasets.

Related papers

• Generalizable Implicit Motion Modeling for Video Frame Interpolation [51.966062283735596]
  Motion is critical in flow-based Video Frame Interpolation (VFI) General Implicit Motion Modeling (IMM) is a novel and effective approach to motion modeling VFI. Our GIMM can be smoothly integrated with existing flow-based VFI works without further modifications.
  arXiv  Detail & Related papers  (2024-07-11T17:13:15Z)
• AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation [80.33846577924363]
  We present All-Pairs Multi-Field Transforms (AMT), a new network architecture for video framegithub. It is based on two essential designs. First, we build bidirectional volumes for all pairs of pixels, and use the predicted bilateral flows to retrieve correlations. Second, we derive multiple groups of fine-grained flow fields from one pair of updated coarse flows for performing backward warping on the input frames separately.
  arXiv  Detail & Related papers  (2023-04-19T16:18:47Z)
• BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation [38.415806547786744]
  A novel 4K video frame interpolator based on bilateral transformer (BiFormer) is proposed in this paper. Extensive experiments demonstrate that the proposed BiFormer algorithm achieves excellent performance on 4K datasets.
  arXiv  Detail & Related papers  (2023-04-05T04:52:23Z)
• TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation [50.49396123016185]
  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.
  arXiv  Detail & Related papers  (2022-07-19T03:37:49Z)
• Enhanced Bi-directional Motion Estimation for Video Frame Interpolation [0.05541644538483946]
  We present a novel yet effective algorithm for motion-based video frame estimation. Our method achieves excellent performance on a broad range of video frame benchmarks.
  arXiv  Detail & Related papers  (2022-06-17T06:08:43Z)
• Triple Motion Estimation and Frame Interpolation based on Adaptive Threshold for Frame Rate Up-Conversion [6.015556590955814]
  In this paper, we propose a novel motion-compensated frame rate up-conversion (MC-FRUC) algorithm. The proposed algorithm creates interpolated frames by first estimating motion vectors using unilateral (jointing forward and backward) and bilateral motion estimation. Since motion-compensated frame along unilateral motion trajectories yields holes, a new algorithm is introduced to resolve this problem.
  arXiv  Detail & Related papers  (2022-03-05T04:39:42Z)
• 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)
• 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.