Image processing *

Developers of smart cameras, smart DVRs, and neural-network video analytics for surveillance systems need AI models capable of operating in real-world street conditions. Out there, nobody walks around with professional cameras, carefully adjusts angles, sets up lighting, records without compression, or follows the common sense taught in cinematography textbooks.

Of course, Gambit can be used for many other tasks, but its main focus is the convenient collection of material FROM video surveillance systems and dataset annotation specifically FOR video surveillance neural networks.

Gambit is not designed for polished photos and Internet reels. Quite the opposite — it is intended for low-quality surveillance archive footage. At SpesLab, we call this kind of content “wild.”

In the previous article I described my “anime factory” in detail — a pipeline that automatically turns episodes into finished Shorts. But inside that system there is one especially important module that deserves a separate deep dive: a virtual camera for automatic reframing.

In this article, I will break down not just an “auto-crop function,” but a full virtual camera algorithm for vertical video. This is exactly the kind of task that looks simple at first glance: you have a horizontal video, you need to turn it into 9:16, keep a person in frame, and avoid making the result look like a jittery autofocus camera from the early 2010s.

But as soon as you try to build it not for a demo, but for a real pipeline, engineering problems immediately show up:

Hi, Habr!

Over the past few months, I have been building a system that I internally call an “anime factory”: it takes a source episode as input and produces a ready-to-publish YouTube Short with dynamic reframing, subtitles, post-processing, and metadata.

What makes it interesting is not just the fact that editing can be automated, but that a significant part of this work can be decomposed into engineering stages: transcription, audio and scene analysis, strong-moment discovery, “virtual camera” control, and a feedback loop based on performance metrics.

In this article, I will show how this pipeline is structured, why I chose a modular architecture instead of an end-to-end black box, where the system broke, and which decisions eventually made it actually usable.

November 20 marked the official launch Nano Banana Pro (Gemini-3-Pro-Image-Preview) with the powerful Gemini 3 Pro as its foundation. This is a more mature tool for design, infographics, and content. We will not only look at the new features and why this particular model is a breakthrough, but we will also see it in action with real examples.

Are you familiar with that feeling of slight panic when your laptop suddenly starts beeping plaintively, and a sinister warning appears on the screen: 'Disk almost full'? This happened to me recently too. I opened File Explorer and was stunned – my 1 TB external drive was filled to the brim – 95% full!

The culprits weren't movies or games, but a giant graveyard of photos. Twelve folders with the generic name 'DCIM,' mountains of screenshots I had copied five times 'just in case,' and heaps of nearly identical sunset shots taken in burst mode. Trying to manually find identical photos was like looking for a needle in a haystack the size of Siberia.

In a previous article, I discussed how to best sort photos, and even then I realized it was time to declare war on duplicates. And that moment has come. After testing more than 15 tools (and wasting a lot of nerves), I've selected 5 free programs that really help solve the problem. I'll share this experience with you.

Image generation by neural networks has become a 'regular button' alongside familiar design tools. Today, you can create an image from a description in Russian, right in your browser, often without registration and, importantly, for free. Such a 'free image generator' is useful not only for designers: entrepreneurs create product cards and hero banners, SMM specialists create ad creatives and stories, journalists and bloggers create illustrations for their materials, and developers create interface prototypes and game mockups.

Why has this topic become so popular?

DocLing in Working with Texts, Languages, and Knowledge — an in-depth overview of the open-source DocLingtoolkit for extracting, structuring, and analyzing data from documents. The article covers approaches to processing multilingual texts, building language- and domain-specific knowledge models, and integrating DocLing into AI and NLP projects. Includes practical examples and recommendations for developers working with large volumes of unstructured data.

Up to a certain point, I sincerely believed that in today’s world manual CAPTCHA recognition was gradually becoming an anachronism, especially when it came to such simple CAPTCHAs as image-based ones—where one merely needs to read text off a photograph and input it as plain text. But as it turns out, things aren’t quite so straightforward (no matter how it may sound).

Among photographers, it is known that on "big" cameras the use of 14-bit readout compared to 12-bit can have a positive impact on shadow detail. How does this apply to small sensors in smartphone cameras?

InvokeAI 2.2 is now available to everyone. This update brings in exciting features, like UI Outpainting, Embedding Management and more. See highlighted updates below, or the full release notes for everything included in the release.

Great for seamless patterns, abstract drawings, and watercolor-styled images. How to use it and train a neural network on your own pictures?

Download the model here: https://huggingface.co/netsvetaev/netsvetaev-free

The InvokeAI team is excited to share our latest feature release, with a set of new features, UI enhancements, and CLI capabilities.

The present invention relates to an analog signal capturing devices generally and monochrome or color image capture sensors, such as a scanner or a Charge-Coupled-Device (“CCD”) for video and photo camera in particular, which are almost free from moiré and aliasing. The present invention relates to methods for enhancing the resolution of an image capture device and device for digital color/grey image displaying also.

Multimodality has led the pack in machine learning in 2021. Neural networks are wolfing down images, text, speech and music all at the same time.  OpenAI is, as usual, top dog, but as if in defiance of their name, they are in no hurry to share their models openly.  At the beginning of the year, the company presented the DALL-E neural network, which generates 256x256 pixel images in answer to a written request.  Descriptions of it can be found as articles on arXiv and examples on their blog.  

As soon as DALL-E flushed out of the bushes, Chinese researchers got on its tail.  Their open-source CogView neural network does the same trick of generating images from text.  But what about here in Russia? One might say that “investigate, master, and train” is our engineering motto.  Well, we caught the scent, and today we can say that we created from scratch a complete pipeline for generating images from descriptive textual input written in Russian.

In this article we present the ruDALL-E XL model, an open-source text-to-image transformer with 1.3 billion parameters as well as ruDALL-E XXL model, an text-to-image transformer with 12.0 billion parameters which is available in DataHub SberCloud, and several other satellite models.

Google Colorizing Transformer vs Deoldify

Every time when the essential question arises, whether to upgrade the cards in the server room or not, I look through similar articles and watch such videos.

Channel with the aforementioned video is very underestimated, but the author does not deal with ML. In general, when analyzing comparisons of accelerators for ML, several things usually catch your eye:

• The authors usually take into account only the "adequacy" for the market of new cards in the United States;
• The ratings are far from the people and are made on very standard networks (which is probably good overall) without details;
• The popular mantra to train more and more gigantic models makes its own adjustments to the comparison;

The answer to the question "which card is better?" is not rocket science: Cards of the 20* series didn't get much popularity, while the 1080 Ti from Avito (Russian craigslist) still are very attractive (and, oddly enough, don't get cheaper, probably for this reason).

All this is fine and dandy and the standard benchmarks are unlikely to lie too much, but recently I learned about the existence of Multi-Instance-GPU technology for A100 video cards and native support for TF32 for Ampere devices and I got the idea to share my experience of the real testing cards on the Ampere architecture (3090 and A100). In this short note, I will try to answer the questions:

• Is the upgrade to Ampere worth it? (spoiler for the impatient — yes);
• Are the A100 worth the money (spoiler — in general — no);
• Are there any cases when the A100 is still interesting (spoiler — yes);
• Is MIG technology useful (spoiler — yes, but for inference and for very specific cases for training);

Общая информация

Разработка апплета для фото на документы самостоятельно

1. Подготовка

1.1 Добавьте репозиторий Maven Huawei в файл на уровне проекта build.gradle