Softmax Splatting for Video Frame Interpolation

CVPR 2020 Simon NiklausFeng Liu

Differentiable image sampling in the form of backward warping has seen broad adoption in tasks like depth estimation and optical flow prediction. In contrast, how to perform forward warping has seen less attention, partly due to additional challenges such as resolving the conflict of mapping multiple pixels to the same target location in a differentiable way... (read more)

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Video Frame Interpolation Middlebury SoftSplat Interpolation Error 4.22 # 1
SSIM 0.971 # 1
PSNR 38.42 # 1
Video Frame Interpolation UCF101 SoftSplat PSNR 35.39 # 1
SSIM 0.952 # 3
Video Frame Interpolation Vimeo90k SoftSplat PSNR 36.10 # 1
SSIM 0.970 # 3

Methods used in the Paper