Paper

Linearized Multi-Sampling for Differentiable Image Transformation

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)

Results in Papers With Code
(↓ scroll down to see all results)