Linearized Multi-Sampling for Differentiable Image Transformation

ICCV 2019 Wei JiangWeiwei SunAndrea TagliasacchiEduard TrullsKwang Moo Yi

We propose a novel image sampling method for differentiable image transformation in deep neural networks. The sampling schemes currently used in deep learning, such as Spatial Transformer Networks, rely on bilinear interpolation, which performs poorly under severe scale changes, and more importantly, results in poor gradient propagation... (read more)

PDF Abstract


No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.