SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.14966 · NeurIPS · 2024

Masked Pre-training Enables Universal Zero-shot Denoiser

Tianle Liu, Xiaoxiao Ma, Ben Wang, Yi Jin, Pengyang Ling, Huaian Chen, Zhixiang Wei, Junkang Dai

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Poisson SwinIR B2U DIP ZS-N2N Ours (b) Generalization (c) Real-world & Medical noise removal Noisy DIP Ours Noisy DIP Ours Figure 1: (a) Ours surpasses current zero-shot methods with reduced inference time (on CSet with Gaussian σ=25, see Sec. 3.2). (b) It shows better generalization across different noise types than current zero-shot & supervised/unsupervised methods (Sec. 3.3). (c) And can remove spatial correlated real-world noise, results are from SIDD benchmark [1] and FMD [2] (Sec. 3.4, Sec. 3.5).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.14966")
get_code_for_paper("2401.14966")
have("2401.14966")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.14966.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.14966.svg)](https://syntology.ai/paper/2401.14966)

Connect an agent — have() is free.