aFarkas/lazysizes
High performance and SEO friendly lazy loader for images (responsive and normal), iframes and more, that detects any visibility changes triggered through user interaction, CSS or JavaScript without configuration. (⭐ 17746)
TeamPiped/http3-ytproxy
A legacy http/2 and http/3 proxy for images and videos, originally designed for use with Invidious, later repurposed for Piped. (⭐ 30)
SuperGaussian: Repurposing Video Models for 3D Super Resolution
We present a simple, modular, and generic method that upsamples coarse 3D models by adding geometric and appearance details. While generative 3D models now exist, they do not yet match the quality of their counterparts in image and video domains. We...
Gas and Dust in the Taffy Galaxies: Ugc12914/15
We present a comprehensive study of the dust and gas properties in the after-head-on-collision UGC12914/15 galaxy system using multi-transition CO data and SCUBA sub-mm continuum images at both 450 and 850$μ$m. CO(3-2) line emission was detected i...
Molecular Gas Concentrations Outside the Merging Disks
We present our preliminary BIMA CO(1-0) images of II~Zw~96 which show huge molecular gas concentrations outside the merging disks. The dominant extra-disk CO concentrations in II~Zw~96 correspond to the two star-forming ``knots'' hidden by dust, wh...
Facebook - Apps on Google Play
Whether you’re thrifting gear, showing reels to that group who gets it, or sharing laughs over fun images reimagined by AI, Facebook helps you make things happen like no other social network.
Some of my favorite images of Richard Nixon
...
microsoft/RegionCLIP
[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining" (⭐ 807)
Region Ensemble Network: Improving Convolutional Network for Hand Pose Estimatio…
Hand pose estimation from monocular depth images is an important and challenging problem for human-computer interaction. Recently deep convolutional networks (ConvNet) with sophisticated design have been employed to address it, but the improvement ov...
Contrastive Region Guidance: Improving Grounding in Vision-Language Models witho…
Highlighting particularly relevant regions of an image can improve the performance of vision-language models (VLMs) on various vision-language (VL) tasks by guiding the model to attend more closely to these regions of interest. For example, VLMs can...
Need help finding this manga(images not in order)
...
MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learnin…
Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices. Typical mangas have simple textures, wide lines, and few color gradients, which are vectoriza...
Barriers in Integrating Medical Visual Question Answering into Radiology Workflo…
Medical Visual Question Answering (MedVQA) is a promising tool to assist radiologists by automating medical image interpretation through question answering. Despite advances in models and datasets, MedVQA's integration into clinical workflows remains...
Outshining in the Spatially Resolved Analysis of a Strongly-Lensed Galaxy at z=6…
We present JWST/NIRCam observations of a strongly-lensed, multiply-imaged galaxy at $z=6.072$, with magnification factors >~20 across the galaxy. We perform a spatially-resolved analysis of the physical properties at scales of ~200 pc, inferred from...
Optimizing Domain-Specific Image Retrieval: A Benchmark of FAISS and Annoy with…
Approximate Nearest Neighbor search is one of the keys to high-scale data retrieval performance in many applications. The work is a bridge between feature extraction and ANN indexing through fine-tuning a ResNet50 model with various ANN methods: FAIS...
The entire Whitty lore and facts made by @sock.clip on Instagram, the creator of…
...
Impressions2Font: Generating Fonts by Specifying Impressions
Various fonts give us various impressions, which are often represented by words. This paper proposes Impressions2Font (Imp2Font) that generates font images with specific impressions. Imp2Font is an extended version of conditional generative adversari...
Font Impression Estimation in the Wild
This paper addresses the challenging task of estimating font impressions from real font images. We use a font dataset with annotation about font impressions and a convolutional neural network (CNN) framework for this task. However, impressions attach...
Gooners felling for AI generated images
bike crowd handle fearless chunky subsequent office yoke hurry memorize *This post was mass deleted and anonymized with [Redact](https://redact.dev/home)*...
Butterfly, Moth, and Skipper Identification - North American Flying …
Online reference cataloguing North American Butterfly and Moth insects through text and imagery.