Search Results for "parallel image segmentation"

Segmentation models with pre trained backbones. High-level API (just two lines to create a neural network) 9 models architectures for binary and multi class segmentation (including legendary Unet) 124 available encoders (and 500+ encoders from timm) All encoders have pre-trained weights for faster and better convergence. Popular metrics and losses for training routines.

Av1an is a command-line encoding framework designed to efficiently encode video into the AV1 format using distributed and parallel processing techniques. It acts as an orchestrator that splits video files into chunks, processes them in parallel using encoders like SVT-AV1, AOM, or rav1e, and then merges the results into a final output. The tool is optimized for high-quality encoding while reducing total processing time through multi-core and multi-machine support. It includes scene detection...

...Unlike most existing methods that perform video matting frame-by-frame as independent images, our method uses a recurrent architecture to exploit temporal information in videos and achieves significant improvements in temporal coherence and matting quality. Furthermore, we propose a novel training strategy that enforces our network on both matting and segmentation objectives. This significantly improves our model's robustness. Our method does not require any auxiliary inputs such as a trimap or a pre-captured background image, so it can be widely applied to existing human matting applications. RVM is specifically designed for robust human video matting.

ThumbsUp! is a multi-threaded image resizing tool originally written in C# .NET 2.0. It was initially developed as an exercise in multi-threaded development, but is also a very functional and blazingly fast thumbnail creator / image resizing tool. I've since reworked it for .NET 4.0 and the new parallel threading libraries. Hope you enjoy it!

audio classification; speaker segmentation; speaker clustering; speaker recognition; spoken document retrieval; image retrieval; video retrieval; etc.

FFRend is a Renderer for FreeFrame plugins. It allows you to chain any number of plugins together, automate their parameters using oscillators, and record the output to a video file. The input is a video, still image, or source plugin. Complex signal routing including feedback is supported. Each plugin potentially runs on its own core, and multiple cores can be assigned to a single plugin.

Fully automated segmentation of moving objects from a stationary scene using pre-stored scene images. Needs no external parameters or settings; all parameters are derived internally from the pre-stored images. Implemented using OpenCV framework.