@bikepedantic@transportation.social2024-02-28 18:06:17
Because City of Cambridge isn't here, i didn't know that the Mass Ave Planning Study had kicked off, and has its first meeting tomorrow, 6-7:30pm.
https://cambridgema.zoom.us/meeting/register/tZAqdeytqjkqGNxUEKNTqybzja_ISwNYOL2X#/registrati…
@inthehands@hachyderm.io2024-02-29 01:29:49
I think this is •really• good news:
https://minnesotareformer.com/2024/02/28/environmental-groups-cities-find-compromise-at-the-capitol-to-end-2040-plan-lawsuit/
The Minneapolis 2040 plan…
@benb@osintua.eu2024-02-28 21:26:12
Explaining Propaganda. Why Zelensky’s Interview Views Fail in Comparison to Putin’s (Tucker Carlson Interview) Written by Matt Wickham, analyst UCMC/HWAG As the hype surrounding the Carlson interview Source : https://uacrisis.org/en/…
@Mediagazer@mstdn.social2024-04-29 17:35:36
Meta confirms it has started testing a limited-time invite-only bonus program for creators on Threads in the US (Ivan Mehta/TechCrunch)
https://techcrunch.com/2024/04/29/meta-confirms-launch-of-a-bonus-program-for-creators-on-thre…
@cheryanne@aus.social2024-04-29 20:44:48
@markhburton@mstdn.social2024-02-29 23:13:47
Gustavo Petro anuncia que Colombia suspende toda compra de armas a Israel - NODAL
https://www.nodal.am/2024/02/gustavo-petro-anuncia-que-colombia-suspende-toda-compra-de-armas-a-israel/
@arXiv_eessIV_bot@mastoxiv.page2024-04-30 07:34:43
Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior
Zhiyuan Li, Yanhui Zhou, Hao Wei, Chenyang Ge, Jingwen Jiang
https://arxiv.org/abs/2404.18820 https://arxiv.org/pdf/2404.18820
arXiv:2404.18820v1 Announce Type: new
Abstract: Compressing images at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. Existing extreme image compression methods generally suffer from heavy compression artifacts or low-fidelity reconstructions. To address this problem, we propose a novel extreme image compression framework that combines compressive VAEs and pre-trained text-to-image diffusion models in an end-to-end manner. Specifically, we introduce a latent feature-guided compression module based on compressive VAEs. This module compresses images and initially decodes the compressed information into content variables. To enhance the alignment between content variables and the diffusion space, we introduce external guidance to modulate intermediate feature maps. Subsequently, we develop a conditional diffusion decoding module that leverages pre-trained diffusion models to further decode these content variables. To preserve the generative capability of pre-trained diffusion models, we keep their parameters fixed and use a control module to inject content information. We also design a space alignment loss to provide sufficient constraints for the latent feature-guided compression module. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in terms of both visual performance and image fidelity at extremely low bitrates.
@primonatura@mstdn.social2024-02-28 13:00:05
"Scientists confirm first cases of bird flu on mainland Antarctica"
#Antarctica #Birds #BirdFlu
@cheryanne@aus.social2024-04-29 20:44:48
@markhburton@mstdn.social2024-02-29 23:13:47
Gustavo Petro anuncia que Colombia suspende toda compra de armas a Israel - NODAL
https://www.nodal.am/2024/02/gustavo-petro-anuncia-que-colombia-suspende-toda-compra-de-armas-a-israel/