HEVC-EPIC: Edge-preserving interpolation of coded HEVC motion with applications to framerate upsampling

Ruefenacht, Dominic; Taubman, David

doi:10.1109/icme.2017.8019515

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our initial proposal of HEVC-EPIC [11], we considered motion coded for unidirectionally predicted P-frames. For such frames, each block is either temporally predicted, which is called "Inter" prediction, or predicted using only spatial information of the target frame (so-called "Intra" prediction).…”

Section: Optical Flowmentioning

confidence: 99%

“…For such frames, each block is either temporally predicted, which is called "Inter" prediction, or predicted using only spatial information of the target frame (so-called "Intra" prediction). In this work, we generalize [11] to bidirectionally predicted B-frames. For ease of explanation, we focus on an IBPB structure, where each B-frame f k is predicted from its immediate temporal neighbours f k−1 and f k+1 ; extensions to more general B-frame structures (e.g., hierarchical B-Frames [13]) can readily be obtained.…”

Section: Optical Flowmentioning

confidence: 99%

“…In the original EPIC method, the correspondences are found using deep matching [10], which accounts for the majority of the overall motion estimation time. In order to avoid the time-consuming estimation of correspondences, we proposed in [11] to use decoded motion vectors as "seeds" for the edge-preserving interpolation strategy (EPIC) [8]; we call the resulting method HEVC-EPIC (HE). These initial explorations were limited to unidirectionally predicted P-frames.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Leveraging decoded HEVC motion for fast, high quality optical flow estimation

Rüfenacht

Taubman

2017

2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)

Self Cite

View full text Add to dashboard Cite

We propose a method of improving the quality of decoded HEVC motion fields attached to B-frames, in order to make them more suitable for video analysis and enhancement tasks. We use decoded HEVC motion vectors as a sparse set of motion "seeds", which guide an edge-preserving affine interpolation of coded motion (HEVC-EPIC) in order to obtain a much more physical representation of the scene motion. We further propose HEVC-EPIC-BI, which adds a bidirectional motion completion step that leverages the fact that regions which are occluded in one direction are usually visible in the other. The use of decoded motion allows us to avoid the time-consuming estimation of "seeds". Experiments on a large variety of synthetic sequences show that compared to a state-of-the-art "seed-based" optical flow estimator, the computational complexity can be reduced by 80%, while incurring no increase at in average EPE at higher bit-rates, and a slight increase of 0.09 at low bit-rates.

show abstract

Section: Optical Flowmentioning

confidence: 99%

Section: Optical Flowmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging decoded HEVC motion for fast, high quality optical flow estimation

Rüfenacht

Taubman

2017

2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)

Self Cite

View full text Add to dashboard Cite

show abstract

HEVC-EPIC: Fast Optical Flow Estimation From Coded Video via Edge-Preserving Interpolation

Rüfenacht

Taubman

2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This paper presents a method leveraging coded motion information to obtain a fast, high quality motion field estimation. The method is inspired by a recent trend followed by a number of top-performing optical flow estimation schemes that first estimate a sparse set of features between two frames, and then use an edge-preserving interpolation scheme (EPIC) to obtain a piecewise-smooth motion field that respects moving object boundaries. In order to skip the time-consuming estimation of features, we propose to directly derive motion seeds from decoded HEVC block motion; we call the resulting scheme "HEVCEPIC". We propose motion seed weighting strategies that account for the fact that some motion seeds are less reliable than others. Experiments on a large variety of challenging sequences and various bit-rates show that HEVC-EPIC runs significantly faster than EPIC flow, while producing motion fields that have a slightly lower average endpoint error (A-EPE). HEVC-EPIC opens the door of seamlessly integrating HEVC motion into video analysis and enhancement tasks. When employed as input to a framerate upsampling scheme, the average Y-PSNR of the interpolated frames using HEVC-EPIC motion slightly outperforms EPIC flow across the tested bit-rates, while running an order of magnitude faster.

show abstract

HEVC-EPIC: Edge-preserving interpolation of coded HEVC motion with applications to framerate upsampling

Cited by 2 publications

References 9 publications

Leveraging decoded HEVC motion for fast, high quality optical flow estimation

Leveraging decoded HEVC motion for fast, high quality optical flow estimation

HEVC-EPIC: Fast Optical Flow Estimation From Coded Video via Edge-Preserving Interpolation

Contact Info

Product

Resources

About