Direction-Select Motion Estimation for Motion-Compensated Frame Rate Up-Conversion

Yoo, Dong-Gon; Kang, Suk‐Ju; Kim, Young Hwan

doi:10.1109/jdt.2013.2263374

Cited by 48 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Twenty known YUV videos in CIF format (352× 288) with 15fps are selected (OnlineVD). Two popular softwares (MSU and MVTools) and two progressive MCFIs (DSME (Yoo, Kang, & Kim, 2013) and MCMP (Li, Gan, Cui, Tang, & Zhu, 2014)) are used. Four target frame-rates (20, 30, 60, and 120) fps are involved.…”

Section: Experimental Results and Discussion Experimental Settingsmentioning

confidence: 99%

“…Motion-Compensation Frame-Interpolation (MCFI) is another special frame based video manipulation, which periodically synthesizes intermediate frames to alleviate the motion discontinuity of low frame-rate videos (Yoo, Kang, & Kim, 2013;Li, Gan, Cui, Tang, & Zhu, 2014). Though MCFI is originally proposed to improve the visual quality or increase the frame-rate of low frame rate videos, it still might be used by a falsifier for malicious purposes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Interpolated Frames by Motion-Compensated Frame-Interpolation via Measuring Irregularity of Optical Flow

Ding

Huang

Zhang

et al. 2022

International Journal of Digital Crime and Forensics

View full text Add to dashboard Cite

Motion-compensated frame-interpolation (MCFI), synthesize intermediate frames between input frames guided by estimated motion, can be employed to falsify high bit-rate videos or high frame-rate videos with different frame-rates. Although existing MCFI identification methods have obtained satisfactory results, they are seriously degraded by stronger compression. Therefore, to conquer this issue, a blind forensics method is proposed to identify the adopted MCFI methods by considering the irregularities of optical flow produced by various MCFIs. In this paper, a set of compact features are constructed from the motion-aligned frame difference-weighted histogram of local binary pattern on the basis of optical flow (MAFD-WHLBP). Experimental results show that the proposed approach outperforms existing MCFI detectors under stronger compression.

show abstract

Section: Experimental Results and Discussion Experimental Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Identification of Interpolated Frames by Motion-Compensated Frame-Interpolation via Measuring Irregularity of Optical Flow

Ding

Huang

Zhang

et al. 2022

International Journal of Digital Crime and Forensics

View full text Add to dashboard Cite

show abstract

“…The performance of the proposed algorithm has been evaluated by comparing it with those of WaME algorithm [16], EBME algorithm [7], Dual ME algorithm [8], and DS-ME algorithm [9] † , and various CIF@30Hz test sequences are used, including Foreman, Carphone, News, Pairs, Football, Stefan, Tennis, Mobile, Bus, City, and Flower. To evaluate the quality of the interpolated frames from subjective and objective views, the first 50 even frames of each test sequence are removed, and then they are reconstructed from the first 51 odd frames using MC-FRUC algorithms.…”

Section: Resultsmentioning

confidence: 99%

“…Moreover, the repetitive patterns existing in video frame also seriously interfere with full search and result in mismatch since the interpolated blocks are not known. To improve the accuracy of conventional BME, the extended BME (EBME) [7] extra calculates MV of the block overlapping with each of two adjacent original blocks by half to find the true MV with higher probability than the conventional BME, the dual ME [8] uses the unidirectional and bidirectional matching ratios of blocks in the previous and following frames to refine the motion vector field (MVF) of interpolated frame, and the direction-select ME (DS-ME) [9] independently calculates the forward and backward MVs of the interpolated frame and then selects the more reliable one from them by using the sum of bilateral absolute differences (SBAD). Although the above-mentioned methods can obtain a more accurate MVF, their performance is improved at the expense of increased computational complexity.…”

Section: Introductionmentioning

confidence: 99%

Wavelet Pyramid Based Multi-Resolution Bilateral Motion Estimation for Frame Rate Up-Conversion

Liu

Chen

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThe conventional bilateral motion estimation (BME) for motion-compensated frame rate up-conversion (MC-FRUC) can avoid the problem of overlapped areas and holes but usually results in lots of inaccurate motion vectors (MVs) since 1) the MV of an object between the previous and following frames is more likely to have no temporal symmetry with respect to the target block of the interpolated frame and 2) the repetitive patterns existing in video frame lead to the problem of mismatch due to the lack of the interpolated block. In this paper, a new BME algorithm with a low computational complexity is proposed to resolve the above problems. The proposed algorithm incorporates multi-resolution search into BME, since it can easily utilize the MV consistency between two adjacent pyramid levels and spatial neighboring MVs to correct the inaccurate MVs resulting from no temporal symmetry while guaranteeing low computational cost. Besides, the multi-resolution search uses the fast wavelet transform to construct the wavelet pyramid, which not only can guarantee low computational complexity but also can reserve the high-frequency components of image at each level while sub-sampling. The high-frequency components are used to regularize the traditional block matching criterion for reducing the probability of mismatch in BME. Experiments show that the proposed algorithm can significantly improve both the objective and subjective quality of the interpolated frame with low computational complexity, and provide the better performance than the existing BME algorithms.

show abstract

“…Although this method showed interpolation image improvement through relatively few calculations, it has a disadvantage in that it cannot predict large motions or morphological changes of objects. In [4], bidirectional motion prediction through the block matching algorithm (BMA) and the interpolation of intermediate frames through motion are refined. BMA has less computational complexity and generates interpolated images with the least flickering, so it is a practical study applicable to actual products.…”

Section: Related Workmentioning

confidence: 99%

Forward Warping-Based Video Frame Interpolation Using a Motion Selective Network

Heo

2022

Electronics

View full text Add to dashboard Cite

Recently, deep neural networks have shown surprising results in solving most of the traditional image processing problems. However, the video frame interpolation field does not show relatively good performance because the receptive field requires a vast spatio-temporal range. To reduce the computational complexity, in most frame interpolation studies, motion is first calculated with the optical flow, then interpolated frames are generated through backward warping. However, while the backward warping process is simple to implement, the interpolated image contains mixed motion and ghosting defects. Therefore, we propose a new network that does not use the backward warping method through the proposed max-min warping. Since max-min warping generates a clear warping image in advance according to the size of the motion and the network is configured to select the warping result according to the warped layer, using the proposed method, it is possible to optimize the computational complexity while selecting a contextually appropriate image. The video interpolation method using the proposed method showed 34.847 PSNR in the Vimeo90k dataset and 0.13 PSNR improvement compared to the Quadratic Video Interpolation method, showing that it is an efficient frame interpolation self-supervised learning.

show abstract

Direction-Select Motion Estimation for Motion-Compensated Frame Rate Up-Conversion

Cited by 48 publications

References 27 publications

Identification of Interpolated Frames by Motion-Compensated Frame-Interpolation via Measuring Irregularity of Optical Flow

Identification of Interpolated Frames by Motion-Compensated Frame-Interpolation via Measuring Irregularity of Optical Flow

Wavelet Pyramid Based Multi-Resolution Bilateral Motion Estimation for Frame Rate Up-Conversion

Forward Warping-Based Video Frame Interpolation Using a Motion Selective Network

Contact Info

Product

Resources

About