HashEncoding: Autoencoding with Multiscale Coordinate Hashing
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 29 Nov 2022.
Builds on
11 of 21 references.
References · 11
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
- 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
- 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 286
- 2020Adversarial Generation of Continuous Imagescited by 135
- 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 106
- 2019COCO-GAN: Generation by Parts via Conditional Coordinatingcited by 67
- 2019Linearized Multi-Sampling for Differentiable Image Transformationcited by 11
Built on by
Not cited yet.