no code implementations • 30 Jul 2023 • Pan Gao, Haoyue Tian, Jie Qin
Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity.
1 code implementation • 6 Dec 2022 • Lihua Fu, Haoyue Tian, Xiangping Bryce Zhai, Pan Gao, Xiaojiang Peng
Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc.
Ranked #378 on Image Classification on ImageNet
1 code implementation • 25 Apr 2022 • Haoyue Tian, Pan Gao, Xiaojiang Peng
In order to solve this problem, we revisit the deformable convolution for video interpolation, which can break the fixed grid restrictions on the kernel region, making the distribution of reference points more suitable for the shape of the object, and thus warp a more accurate interpolation frame.
1 code implementation • 11 Feb 2022 • Haoyue Tian, Pan Gao, Ran Wei, Manoranjan Paul
Motion estimation and motion compensation are indispensable parts of inter prediction in video coding.