HashEncoding: Autoencoding with Multiscale Coordinate Hashing
We present HashEncoding, a novel autoencoding architecture that leverages a non-parametric multiscale coordinate hash function to facilitate a per-pixel decoder without convolutions. By leveraging the space-folding behaviour of hashing functions, HashEncoding allows for an inherently multiscale embedding space that remains much smaller than the original image. As a result, the decoder requires very few parameters compared with decoders in traditional autoencoders, approaching a non-parametric reconstruction of the original image and allowing for greater generalizability. Finally, by allowing backpropagation directly to the coordinate space, we show that HashEncoding can be exploited for geometric tasks such as optical flow.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderOptical Flow EstimationSimilar Papers 제목 키워드 기반
GIST: Towards Photorealistic Style Transfer via Multiscale Geometric Representations
State-of-the-art Style Transfer methods often leverage pre-trained encoders optimized for discriminative tasks, which may not be ideal for image synthesis. This can result in significant artifacts and loss of photorealis…
Image GenerationStyle TransferMultiscale Softmax Cross Entropy for Fovea Localization on Color Fundus Photography
Fovea localization is one of the most popular tasks in ophthalmic medical image analysis, where the coordinates of the center point of the macula lutea, i.e. fovea centralis, should be calculated based on color fundus im…
Medical Image AnalysisMultiscale scattered data analysis in samplet coordinates
We study multiscale scattered data interpolation schemes for globally supported radial basis functions with focus on the Mat\'ern class. The multiscale approximation is constructed through a sequence of residual correcti…
Reflectance Hashing for Material Recognition
We introduce a novel method for using reflectance to identify materials. Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionalit…
Dictionary LearningMaterial RecognitionWeakly-paired Cross-Modal Hashing
Hashing has been widely adopted for large-scale data retrieval in many domains, due to its low storage cost and high retrieval speed. Existing cross-modal hashing methods optimistically assume that the correspondence bet…
ClusteringRetrieval