Search Results for "video frames" - Page 2
Sort By:
Showing 45 open source projects for "video frames"
View related business solutions-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
UCO3D
Uncommon Objects in 3D dataset
uCO3D is a large-scale 3D vision dataset and toolkit centered on turn-table videos of everyday objects drawn from the LVIS taxonomy. It provides about 170,000 full videos per object instance rather than still frames, along with per-video annotations including object masks, calibrated camera poses, and multiple flavors of point clouds. Each sequence also ships with a precomputed 3D Gaussian Splat reconstruction, enabling fast, differentiable rendering workflows and modern implicit/point-based modeling experiments. The repository includes automated downloaders with checksum verification, fine-grained controls to fetch only selected modalities or super-categories, and a lightweight Python API for loading frames, geometry, and splats on demand. ... -
2
BoxMOT
Pluggable SOTA multi-object tracking modules for segmentation
BoxMOT is an open-source framework designed to provide modular implementations of state-of-the-art multi-object tracking algorithms for computer vision applications. The project focuses on the tracking-by-detection paradigm, where objects detected by vision models are continuously tracked across frames in a video sequence. It provides a pluggable architecture that allows developers to combine different object detectors with multiple tracking algorithms without modifying the core codebase. The framework supports integration with detection, segmentation, and pose estimation models that produce bounding box outputs. It also includes evaluation tools and benchmarking pipelines that allow researchers to test tracking performance on standard datasets such as MOT17 and MOT20. ... -
3
Fast3R
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
...It represents a next-generation feedforward 3D reconstruction model capable of producing dense point clouds and camera poses for hundreds to thousands of images or video frames in a single inference pass—eliminating the need for slow, iterative structure-from-motion pipelines. Built on PyTorch Lightning and extending concepts from DUSt3R and Spann3r, Fast3R unifies multi-view geometry, depth estimation, and camera registration within a single transformer-based architecture. It outputs high-quality 3D scene representations from unordered or sequential views, scaling to large datasets and varied camera intrinsics. ... -
4
Lyra 2
Project Lyra: Open Generative 3D World Models
The Lyra 2 project is a research-driven framework developed by NVIDIA that focuses on building open generative 3D world models using advanced diffusion-based techniques. It enables the creation of fully explorable 3D environments from minimal inputs such as a single image or video, leveraging self-distillation methods to generate consistent spatial representations. The system evolves across versions, with newer iterations introducing long-horizon generation and improved 3D consistency across frames. It combines elements of computer vision, generative modeling, and spatial intelligence to produce dynamic and navigable virtual worlds. ... -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
HunyuanOCR
OCR expert VLM powered by Hunyuan's native multimodal architecture
HunyuanOCR is an open-source, end-to-end OCR (optical character recognition) Vision-Language Model (VLM) developed by Tencent‑Hunyuan. It’s designed to unify the entire OCR pipeline, detection, recognition, layout parsing, information extraction, translation, and even subtitle or structured output generation, into a single model inference instead of a cascade of separate tools. Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a... -
6
cleanvideo-cli
CLI tool for removing watermarks from AI-generated videos using frame-
cleanvideo-cli is a command-line tool designed to remove visible watermarks from AI-generated videos. It works by analyzing video frames and reconstructing the underlying pixels in watermark regions, without cropping or blurring the original content. This project is intended for developers, researchers, and creators who need a lightweight utility for cleaning preview or draft videos before further processing. Note: This tool does not bypass platform restrictions and should be used only on content you own or have the rights to use. -
7
h2oGPT
Private chat with local GPT with document, images, video, etc.
h2oGPT is an open-source platform that allows users to interact with local GPT models in a completely private environment. It supports a variety of document types, including PDFs, Word files, images, video frames, and even audio, enabling users to query and analyze their documents or engage in a private chat with AI. The platform is designed to be secure and offline, ensuring that all data remains private and under the user's control. h2oGPT supports several AI models, including oLLaMa and Mixtral, making it a flexible tool for anyone needing advanced document analysis and AI-driven conversation in a secure, local setup. -
8
AI-Aimbot
CS2, Valorant, Fortnite, APEX, every game
AI-Aimbot is a computer vision project that demonstrates how artificial intelligence can be used to automatically identify and target opponents in video games. The system uses an object detection model based on the YOLOv5 architecture to detect human-shaped characters in gameplay screenshots or video frames. Once a target is identified, the program automatically adjusts the player’s aim toward the detected target, effectively automating the aiming process in first-person shooter games. ... -
9
pipeless
A computer vision framework to create and deploy apps in minutes
...Pipeless is inspired by modern serverless technologies. It provides the development experience of serverless frameworks applied to computer vision. You provide some functions that are executed for new video frames and Pipeless takes care of everything else. You can easily use industry-standard models, such as YOLO, or load your custom model in one of the supported inference runtimes. Pipeless ships some of the most popular inference runtimes, such as the ONNX Runtime, allowing you to run inference with high performance on CPU or GPU out-of-the-box. ... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
10
The main purpose of this program is to provide functionality for extract hardcoded subtitles (hardsub) from video. It provides two main features: 1) Autodetection of frames with hardcoded text (hardsub) on video with saving info about timing positions. 2) Generation of cleared from background text images, which allows with usage of OCR programs (like FineReader, Subtitle Edit, Google Drive) to generate complete subtitles with original text and timing. ...
-
11
AI Atelier
Based on the Disco Diffusion, version of the AI art creation software
Based on the Disco Diffusion, we have developed a Chinese & English version of the AI art creation software "AI Atelier". We offer both Text-To-Image models (Disco Diffusion and VQGAN+CLIP) and Text-To-Text (GPT-J-6B and GPT-NEOX-20B) as options. Making available complete source code of licensed works and modifications, which include larger works using a licensed work, under the same license. Copyright and license notices must be preserved. When a modified version is used to provide a... -
12
TimeSformer
The official pytorch implementation of our paper
TimeSformer is a vision transformer architecture for video that extends the standard attention mechanism into spatiotemporal attention. The model alternates attention along spatial and temporal dimensions (or designs variants like divided attention) so that it can capture both appearance and motion cues in video. Because the attention is global across frames, TimeSformer can reason about dependencies across long time spans, not just local neighborhoods. -
13
Deep Exemplar-based Video Colorization
The source code of CVPR 2019 paper "Deep Exemplar-based Colorization"
...In order to colorize your own video, it requires to extract the video frames, and provide a reference image as an example. -
14
VoTT
Visual Object Tagging Tool, an electron app for building models
Visual Object Tagging Tool: An electron app for building end-to-end Object Detection Models from Images and Videos. An open source annotation and labeling tool for image and video assets. VoTT is a React + Redux Web application, written in TypeScript. This project was bootstrapped with Create React App. VoTT can be installed as a native application or run from source. VoTT is also available as a stand-alone Web application and can be used in any modern Web browser. VoTT is available for... -
15
vid2vid
Pytorch implementation of our method for high-resolution
vid2vid is a deep learning framework for high-resolution video-to-video translation that generates photorealistic videos from structured inputs such as semantic maps, pose sequences, or edge maps. Built on top of image-to-image translation techniques like pix2pixHD, it extends these ideas into the temporal domain by ensuring consistency across video frames. The system can synthesize complex outputs such as realistic talking faces, human motion animations, or dynamic street scenes by learning temporal relationships between frames. -
16
DetectAndTrack
The implementation of an algorithm presented in the CVPR18 paper
DetectAndTrack is the reference implementation for the CVPR 2018 paper “Detect-and-Track: Efficient Pose Estimation in Videos,” focusing on human keypoint detection and tracking across video frames. The system combines per-frame pose detection with a tracking mechanism to maintain identities over time, enabling efficient multi-person pose estimation in video. Code and instructions are organized to replicate paper results and to serve as a starting point for researchers working on pose in video. Although the repo has been archived and is now read-only, its issue tracker and artifacts remain useful for understanding implementation details and experimental settings. ... -
17
Five video classification methods
Code that accompanies my blog post outlining five video classification
...This reduces model complexity, training time, and a whole whack load of hyperparameters we don’t have to worry about. Every video will be subsampled down to 40 frames. So a 41-frame video and a 500-frame video will both be reduced to 40 frames, with the 500-frame video essentially being fast-forwarded. We won’t do much preprocessing. A common preprocessing step for video classification is subtracting the mean, but we’ll keep the frames pretty raw from start to finish. -
18
JAABA
The Janelia Automated Animal Behavior Annotator
The Janelia Automatic Animal Behavior Annotator (JAABA) is a machine learning-based system that enables researchers to automatically compute interpretable, quantitative statistics describing video of behaving animals. Through our system, users encode their intuition about the structure of behavior by labeling the behavior of the animal, e.g. walking, grooming, or following, in a small set of video frames. JAABA uses machine learning techniques to convert these manual labels into behavior detectors that can then be used to automatically classify the behaviors of animals in large data sets with high throughput. ... -
19
OpenTLD
OpenTLD is an open source library for real-time 2D tracking
OpenTLD is an open source implementation of the TLD (Tracking-Learning-Detection) framework, designed for real-time 2D tracking of a single object in video sequences. Because it fuses tracking and detection, TLD can recover from occlusions, drift, or failures by using its detection mechanism to reacquire the object. In terms of usage, one typically initializes the tracker by providing a bounding box on the first frame, then calls a function like run_TLD to process a video and obtain bounding boxes over time. ... -
20
Gemma 4
Google’s flagship dense multimodal model for coding and reasoning
Gemma 4 is Google DeepMind’s flagship dense open-weight multimodal model, designed for high-end reasoning, coding, agentic workflows, and multimodal understanding. The model contains approximately 30.7B parameters and supports text and image inputs with text generation output, while also processing video as image-frame sequences. Built as the most capable model in the Gemma 4 family, it combines strong reasoning performance with a large 256K-token context window and configurable thinking...
