IEEE

Self-Supervised Blind Image Deconvolution via Deep Generative Ensemble Learning

Abstract: Blind image deconvolution (BID) is about recovering a latent image with sharp details from its blurred observation generated by the convolution with an unknown smoothing kernel. Recently, ...
IEEE

Blind Image Deconvolution Using Variational Deep Image Prior

Abstract: Conventional deconvolution methods utilize hand-crafted image priors to constrain the optimization. While deep-learning-based methods have simplified the optimization by end-to-end training, ...
GitHub

L1000 peak deconvolution based on Bayesian analysis

This project is intended to generate high quality perturbagen signatures from LINCS L1000 assay. We build a pipeline, in parallel with L1000 group, to process raw fluorescent intensity data into ...
GitHub

Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer (TPAMI 2023)

2023-01 [NEW:tada:] This repository now contains the code of the ICCV paper and the extra contents of the extended version, including: 2. SnowflakeNet: Point Cloud Completion by Snowflake Point ...