Search Results for "depth-violet"
Sort By:
Showing 501 open source projects for "depth-violet"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Depth Pro
Sharp Monocular Metric Depth in Less Than a Second
Depth Pro is a foundation model for zero-shot metric monocular depth estimation, producing sharp, high-frequency depth maps with absolute scale from a single image. Unlike many prior approaches, it does not require camera intrinsics or extra metadata, yet still outputs metric depth suitable for downstream 3D tasks. Apple highlights both accuracy and speed: the model can synthesize a ~2.25-megapixel depth map in around 0.3 seconds on a standard GPU, enabling near real-time applications. ... -
2
-
3
Depth Anything 3
Recovering the Visual Space from Any Views
Depth Anything 3 is a research-driven project that brings accurate and dense depth estimation to any input image or video, enabling foundational understanding of 3D structure from 2D visual content. Designed to work across diverse scenes, lighting conditions, and image types, it uses advanced neural networks trained on large, heterogeneous datasets, producing depth maps that reveal scene depth relationships and object surfaces with strong fidelity. -
4
Violet is a UML editor with these benefits: Very easy to learn and use. Draws nice-looking diagrams. Completely free. Cross-platform. Violet is intended for developers, students, teachers, and authors who need to produce simple UML diagrams quickly. Want to contribute ? Source code is hosted on github : https://github.com/violetumleditor/violetumleditor
-
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.
-
5
Intel RealSense
Intel® RealSense SDK
Intel® RealSense™ SDK 2.0 is a cross-platform library for Intel® RealSense™ depth cameras. The SDK allows depth and color streaming and provides intrinsic and extrinsic calibration information. The library also offers synthetic streams (point cloud, depth aligned to color and vise-versa), and built-in support for recording and playback of streaming sessions. Intel has EOLed the LiDAR, Facial Authentication, and Tracking product lines. -
6
VGGT-Ω
[CVPR 2026 Oral] VGGT Omega
VGGT-Omega is a Facebook Research computer vision project for feed-forward camera and depth reconstruction. It takes images as input and predicts camera parameters, depth maps, confidence values, and related scene tokens. The project is associated with 3D understanding workflows where models infer scene geometry without a traditional multi-stage reconstruction pipeline. It includes pretrained model variants with different resolutions and text-alignment capabilities, though checkpoint access may require approval. ... -
7
-
8
mosdepth
fast BAM/CRAM depth calculation for WGS, exome, or targeted sequencing
mosdepth is a fast BAM/CRAM depth calculation tool for genomic data, allowing efficient computation of sequencing coverage. -
9
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
...The architecture incorporates advanced techniques such as mixture-of-experts routing, adaptive computation time, and multiple attention mechanisms to dynamically allocate compute where needed. It is highly configurable through a centralized configuration system, allowing experimentation with different architectural parameters such as loop depth, attention type. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
Map-Anything
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
...Instead of stitching together many task-specific models, it uses a single architecture that supports a wide range of 3D tasks—multi-image structure-from-motion, multi-view stereo, monocular metric depth, registration, depth completion, and more. The model flexibly accepts different input combinations (images, intrinsics, poses, sparse or dense depth) and produces a rich set of outputs including per-pixel 3D points, camera intrinsics, camera poses, ray directions, confidence maps, and validity masks. Its inference path is fully feed-forward with optional mixed-precision and memory-efficient modes, making it practical to scale to long image sequences while keeping latency predictable. -
11
DLSS 5 Feeder
DLSS 5 neural rendering in D3D11/D12/Vulkan games
DLSS5-Feeder is a ReShade-based compatibility project that brings DLSS 5 neural rendering into games that do not natively implement DLSS. It constructs the DLAA-style inputs expected by NVIDIA's neural rendering pipeline from the game frame, depth information, and estimated motion vectors. The generated request is processed through a private D3D12 device and then returned to the game's rendering chain. The project supports D3D11, D3D12, Vulkan, OpenGL, and translated older DirectX games, including selected 32-bit titles. A cross-process helper provides access to NVIDIA functionality that is otherwise unavailable inside 32-bit applications. ... -
12
Spatie Crawler
An easy to use, powerful crawler implemented in PHP
...It can be used for web scraping, link checking, or automated testing of web pages. The library is simple to use and supports customizable crawling strategies, including controlling crawl depth and handling redirects. It’s suitable for building crawlers that navigate large or dynamically generated websites. -
13
VGGT
[CVPR 2025 Best Paper Award] VGGT
VGGT is a transformer-based framework aimed at unifying classic visual geometry tasks—such as depth estimation, camera pose recovery, point tracking, and correspondence—under a single model. Rather than training separate networks per task, it shares an encoder and leverages geometric heads/decoders to infer structure and motion from images or short clips. The design emphasizes consistent geometric reasoning: outputs from one head (e.g., correspondences or tracks) reinforce others (e.g., pose or depth), making the system more robust to challenging viewpoints and textures. ... -
14
watercrawl
AI-ready web crawler that extracts and structures website content
...It enables developers and researchers to crawl web pages, extract meaningful information, and convert it into formats that are easier to process and analyze. It provides a modern crawling system that can automatically navigate links, control crawl depth, and collect content from targeted sections of a website. WaterCrawl supports customizable extraction rules so users can focus only on relevant elements while ignoring unnecessary page components. WaterCrawl also offers real-time monitoring capabilities, allowing users to track crawling progress, performance metrics, and errors during large data collection jobs. ... -
15
PostHog Browser JS Library
Send usage data from your web app or site to PostHog
PostHog JS is the JavaScript SDK for integrating PostHog's product analytics into web applications. It allows developers to track user interactions, analyze behavior, and improve app performance based on user data. -
16
crwlr
Library for Rapid (Web) Crawler and Scraper Development
...A crawler could just load actually all links it is finding (and is allowed to load according to the robots.txt file), then it would just load the whole internet (if the URL(s) it starts with are no dead end). Or it can be restricted to load only links matching certain criteria (on same domain/host, URL path starts with "/foo",...) or only to a certain depth. A depth of 3 means 3 levels deep. Links found on the initial URLs provided to the crawler are level 1 and so on. -
17
-
18
Qwen-Image
Qwen-Image is a powerful image generation foundation model
...Qwen-Image supports sophisticated editing tasks such as style transfer, object insertion and removal, detail enhancement, and even human pose manipulation, making it suitable for both professional and casual users. It also includes advanced image understanding capabilities like object detection, semantic segmentation, depth and edge estimation, and novel view synthesis. -
19
AI Agents for Beginners
12 Lessons to Get Started Building AI Agents
...It covers key topics such as prompt design, tool integration, memory management, and multi-agent coordination. The repository is structured to be accessible to beginners while still providing depth for more advanced learners. It also includes practical examples that demonstrate how agents can be applied to real-world problems. Overall, it serves as a foundational resource for understanding and building agent-based AI systems. -
20
katana
Fast CLI web crawler for discovering endpoints in modern web apps
...Through headless browsing, it can analyze dynamic content and single-page applications built with modern frameworks, improving its ability to uncover hidden paths and assets. Katana offers flexible configuration options such as depth control, concurrency limits, and filtering mechanisms to refine results and manage scanning scope. -
21
KaTrain
Improve your Baduk skills by training with KataGo
KaTrain is an advanced training and analysis tool for the board game Go that leverages the powerful KataGo AI engine to provide real-time feedback and in-depth game review capabilities. It is designed to help players of all skill levels improve by identifying mistakes, analyzing move efficiency, and offering alternative strategies based on AI evaluation. The application allows users to play against AI opponents with adjustable difficulty, including intentionally weakened versions of the engine that simulate human-like play styles. ... -
22
CS-Ebook
Curated list of classic, high-quality computer science books
CS-Ebook is a curated repository that compiles high-quality and classic computer science books across a wide range of software-related fields. It focuses on depth over volume, selecting only well-regarded titles that support structured learning and long-term skill development. It spans core areas such as computer fundamentals, programming languages, software engineering, mathematics, data science, and artificial intelligence, making it suitable for learners at different stages. Rather than hosting files, the project serves as a discovery guide, helping users identify essential reading materials and build a strong technical foundation. ... -
23
Open Deep Research
An AI-powered research assistant that performs iterative research
...Its core goal is to provide the simplest possible implementation of a deep research workflow so developers can study and extend agent behavior without dealing with large, opaque codebases. The system exposes parameters such as breadth and depth to control how widely and how deeply the agent explores information sources. It is intentionally kept compact, with a codebase under roughly 500 lines, making it highly approachable for experimentation and learning. The architecture demonstrates how modern agent pipelines can continuously gather evidence, extract learnings, and adjust research direction over time. -
24
WanGP
AI video generator optimized for low VRAM and older GPUs use
...Wan2GP provides a full web-based interface that simplifies interaction with complex generative pipelines, making it easier to configure prompts, models, and rendering settings. It also integrates a wide range of utilities such as prompt enhancement, mask editing, motion design, and extraction tools for pose, depth, and flow data to support advanced video workflows. -
25
fklearn
Functional Machine Learning
fklearn uses functional programming principles to make it easier to solve real problems with Machine Learning.
