Content & Design

Mediapipe Face Mesh 3d is an AI tool designed to generate 3D face meshes from uploaded images. Utilizing the Mediapipe framework, it allows users to create detailed 3D-gltf face models. The tool offers several customization options, including smoothing the mesh, adjusting the depth ratio, and choosing whether to include inner eyes and mouth details. Once generated, the 3D model can be viewed directly within the application. This makes it a versatile tool for various applications requiring 3D facial reconstruction from 2D images, providing a straightforward way to transform a static image into an interactive 3D representation.

DSNeRF (Depth-supervised Neural Radiance Fields) is an open-source PyTorch implementation designed to enhance the training of neural radiance fields. It significantly improves the process by incorporating depth supervision derived from 3D point clouds, which are typically generated during structure-from-motion (SFM) but often overlooked. This innovative approach allows for the training of NeRF models with considerably fewer input views and achieves faster training times. DSNeRF is particularly valuable for researchers and developers working in computer vision and 3D graphics who aim to optimize NeRF model creation and efficiency. The project provides code, pre-trained models, and tutorials for integration, making it accessible for those looking to implement depth-supervised loss in their own projects.

Gaussian Splatting Notes is a free, open-source educational resource offering a comprehensive breakdown of the mathematical formulae behind Gaussian Splatting. This guide, presented as a text version of an explanatory stream, delves into the intricacies of the rasterization process, specifically covering the forward and backward passes. It aims to provide as many details as possible, highlighting core algorithmic concepts and referencing original code snippets to aid understanding. The resource also includes important insights marked with '💡' and clarifies complex topics like 3D covariance reparametrization and 2D Gaussian projection, making it an invaluable aid for those studying this advanced 3D rendering technique.

Gauzilla is a 3D Gaussian Splatting (3DGS) renderer developed in Rust for WebAssembly, featuring lock-free multithreading for platform-agnostic web deployment. It leverages WebGL and CPU splat sorting to ensure high compatibility across various web browsers. The tool can securely load .ply or .splat files from local machines using `rfd` and asynchronously loads .splat files from URLs without requiring async Rust code. Additionally, it supports loading .spz files via a WASM module compiled from the official C++ implementation. Gauzilla is designed for real-time photorealistic rendering of scenes reconstructed from images and videos, making it suitable for Novel View Synthesis applications.

nerfstudio is an open-source, collaboration-friendly studio designed for creating, training, and testing Neural Radiance Fields (NeRFs). It provides a simple API that streamlines the end-to-end process of NeRF development, from data capture to rendering. The library supports a modular implementation of NeRFs, making each component more interpretable and easier to build upon. Developed by Berkeley students and community contributors, nerfstudio aims to foster a community where users can easily contribute and explore NeRF technology. It includes a web-based visualizer for real-time training interaction, support for multiple logging interfaces like Tensorboard and Wandb, and full pipeline support for processing data from various devices like phones with LiDAR. The project emphasizes learning resources, tutorials, and documentation to help users get started and advance their understanding of NeRFs.

SuGaR (Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering) is a PyTorch implementation designed to extract precise and extremely fast meshes from 3D Gaussian Splatting reconstructions. It introduces a regularization term that aligns 3D Gaussians with the scene's surface, allowing for efficient point sampling and mesh extraction using Poisson reconstruction. This method preserves details and is significantly faster than traditional Neural SDFs. SuGaR also offers an optional refinement strategy that binds Gaussians to the mesh surface, enabling joint optimization for easy editing, sculpting, rigging, and animation in traditional software like Blender, Unity, or Unreal Engine. This allows users to retrieve an editable mesh for realistic rendering within minutes, offering superior rendering quality compared to state-of-the-art methods.

Video Depth Anything is an AI tool designed to process input videos and generate corresponding depth videos. This application visualizes the depth information present in each frame of a video, making it suitable for various applications such as 3D video reconstruction, visual effects creation, and AI research. Users can easily upload their video files and customize settings like resolution and frames per second (FPS) to achieve desired outputs. The tool is hosted on Hugging Face Spaces, indicating its accessibility and potential for community-driven development and use. Its primary function is to provide a clear, frame-by-frame depth map, offering a foundational component for advanced video analysis and manipulation.

WebWorldWind is an Open Source JavaScript SDK developed by NASA, with contributions from the European Space Agency, designed for creating geo-browser web applications. It allows developers to embed a 3D globe directly into HTML5 web pages, providing a geographic context with terrain and various shapes for displaying and interacting with geo-located information in both 3D and 2D. The SDK automatically retrieves high-resolution terrain and imagery from remote servers as needed, while also supporting custom terrain, imagery, 3D shapes, and position markings. Key features include improvements to COLLADA 3D model support, the ability to obtain click locations in 3D models, and enhanced Well-Known Text format support. It is licensed under the Apache License, Version 2.0.

Agentheroes is an AI tool designed to generate, animate, and schedule AI characters. It enables users to train custom LoRA models using existing images through services like Fal.ai and Replicate. Once models are trained, users can generate new pictures, which can then be converted into animated videos. A key feature is the ability to schedule these videos for publication on social media platforms, currently supporting X (formerly Twitter). The platform also supports building agentic flows to automate the entire process, allowing for scheduled triggers or API-based activation. This comprehensive workflow makes it suitable for creators looking to streamline their character animation and social media content pipelines.

The 3D Book Image CSS Generator is a specialized tool designed to transform a standard book cover image into a dynamic 3D representation. Users can input the absolute URL of their book cover and then fine-tune various parameters such as perspective and thickness to achieve the desired visual effect. Once customized, the tool generates the necessary HTML and CSS code, which can then be easily embedded directly into any website. This eliminates the need for complex 3D modeling software or extensive coding knowledge, making it accessible for authors, publishers, and web developers looking to showcase books with an engaging visual flair. The project is open-source, encouraging contributions and further development.

Marigold Depth Completion is an AI tool designed to generate detailed depth maps by combining an input image with sparse depth data. Users provide an image and a corresponding sparse depth map file, typically in a numpy format, to produce a comprehensive depth map. This application is particularly useful for tasks requiring accurate 3D scene understanding, such as in computer vision, robotics, and graphics processing. Developed by the Photogrammetry and Remote Sensing Lab of ETH Zurich, it offers a robust solution for enhancing depth information from incomplete datasets, making it a valuable resource for researchers and developers working with 3D data.

MMTracking is an open-source video perception toolbox built on PyTorch, forming a key part of the OpenMMLab project. It stands out as the first open-source toolbox to unify diverse video perception tasks, including video object detection (VID), multiple object tracking (MOT), single object tracking (SOT), and video instance segmentation (VIS) within a single framework. Its modular design allows users to easily construct customized methods by combining different components. MMTracking is known for its simplicity, speed, and strength, leveraging MMDetection for detector integration and running all operations on GPUs for fast training and inference. It reproduces state-of-the-art models, often outperforming official implementations, and supports a wide range of datasets and methods for each task.

React Native Godot enables developers to seamlessly integrate the Godot Engine into their React Native applications, supporting both Android and iOS platforms. Developed by Born and Migeran, this tool offers a stable and robust solution for embedding Godot content, currently serving millions of users in Born's applications. Key features include the ability to start, stop, and restart the Godot Engine, with options to reconfigure and load different Godot apps upon restart. It also supports pausing and resuming Godot instances without shutting them down. The engine runs on a separate thread, ensuring it does not impact the main application or React Native JavaScript threads. Developers can embed Godot's main window and subwindows directly into React Native screens and access the entire Godot API from TypeScript/JavaScript, allowing for object instantiation, method calls, property manipulation, and signal connections.

SUSTechPOINTS, hosted on GitHub, provides a comprehensive platform for software development, offering various plans tailored for individuals and organizations. The Free plan includes unlimited public/private repositories, Dependabot security updates, 2,000 CI/CD minutes/month, and 500MB of Packages storage. The Team plan expands on this with access to GitHub Codespaces, repository rules, multiple reviewers in pull requests, and increased CI/CD minutes and package storage. For larger organizations, the Enterprise plan adds advanced security, compliance features like SOC1/SOC2 reports, data residency options, and extensive support, making it suitable for managing complex projects and teams.

splatviz is a comprehensive, open-source Python-based interactive viewer designed for real-time editing and analysis of 3D Gaussian Splatting scenes. Utilizing the pyimgui GUI library, it enables direct manipulation of Gaussian Python objects just before rendering, offering extensive editing and visualization capabilities. Users can view multiple scenes simultaneously, either side-by-side or in a split-screen view, and evaluate Python expressions on the resulting scene. Key features include an Edit Widget for real-time manipulation of Gaussian parameters, an Eval Widget for debugging and visualizing variables, and a Camera Widget with Orbit and WASD modes for flexible scene navigation. It also supports attaching to running 3DGS training sessions for live inspection and editing.

Unique3D is an open-source project designed for high-quality and efficient 3D mesh generation from a single image. Developed by AiuniAI, this tool leverages AI to create detailed 3D models, making it suitable for various 3D content creation tasks. It supports 3D reconstruction from single-view wild images, producing textured meshes in approximately 30 seconds. The project is continuously under construction, with plans for further features like ComfyUI and Docker support, as well as training code release. Users can run a local Gradio demo for interactive inference and benefit from detailed installation guides for both Linux and Windows systems. Unique3D is particularly sensitive to input image characteristics, performing best with orthographic front-facing images to avoid squashed or incomplete reconstructions.

AliceVision is an open-source photogrammetric computer vision framework designed for 3D reconstruction and camera tracking. It provides a robust software foundation with state-of-the-art computer vision algorithms that can be tested, analyzed, and reused. The project is a collaborative effort between academia and industry, ensuring cutting-edge algorithms meet the quality and robustness required for production use. It allows users to infer the geometry of a scene from a set of unordered photographs or videos, effectively reversing the 3D scene to 2D projection process. The framework is primarily used through Meshroom, which offers both a user interface and a command-line tool for launching the AliceVision pipeline and customizing workflows with Python scripting.

awesome-3D-gaussian-splatting is an open-source, curated collection of resources dedicated to 3D Gaussian Splatting (3DGS) and related technologies. This GitHub repository serves as a central hub for researchers, developers, and enthusiasts to explore papers, implementations, viewers, and learning materials. It aims to keep pace with the rapid advancements in 3DGS, offering a comprehensive database of academic papers, various community and official implementations across different programming languages, and support for popular game engines like Unity and Unreal. Additionally, it lists numerous viewers, including web-based, desktop, and VR options, alongside essential tools and utilities for data processing and development. The repository also provides extensive learning resources, including blog posts, talks, and video tutorials, making it an invaluable resource for anyone looking to understand or contribute to the 3DGS domain.

Mapanything Gradio is a Hugging Face Space application developed by Facebook that specializes in generating detailed 3D models and depth maps from uploaded images or videos. The tool reconstructs visual data, offering comprehensive visualizations of both depth and surface normals. This functionality enables users to perform precise measurements directly on the reconstructed 3D models. Hosted on Hugging Face, it leverages advanced AI capabilities to transform 2D inputs into rich 3D representations, making it a valuable resource for tasks requiring spatial analysis and 3D reconstruction from visual media.

AvatarCLIP is an open-source research project from SIGGRAPH 2022 that provides a powerful solution for zero-shot text-driven generation and animation of 3D avatars. Users can generate detailed 3D avatar shapes and textures from simple text descriptions, such as "a tall and skinny female soldier." The tool also supports motion generation, allowing users to animate their creations with text prompts like "arguing" or "running." A key feature is the ability to convert generated avatars into animatable FBX format, making them compatible with popular 3D software like Blender and Unity3D, or for upload to platforms like Mixamo for access to extensive motion libraries. The project offers a Colab Demo for avatar generation and provides comprehensive instructions for installation and data preparation.

Awesome-holistic-3d is a valuable open-source resource for researchers and academics focused on holistic 3D reconstruction in computer vision. This GitHub repository compiles a comprehensive list of relevant papers, datasets, and code, categorized by scene-level and object-level reconstruction. It includes references to tutorials, workshops, and a wide array of research papers spanning from 2009 to 2020. The resource details various datasets with information on the number of scenes, rooms, frames, and annotated structures, making it an essential reference for anyone working on or studying 3D reconstruction techniques.

GetBito.com is presented as a premium domain name available for purchase through Atom. The domain is described as dynamic, versatile, and memorable, ideal for startups in sectors like cryptocurrency, fintech, or e-commerce. Atom ensures secure transactions, holding payments until the domain is successfully transferred, and guarantees fast transfers, often within hours. Buyers can choose from flexible payment options, including full payment via credit card, crypto, or wire transfer, or installment plans. The platform also offers a Purchase Protection Program, guaranteeing a full refund if the domain cannot be transferred.

splat offers a WebGL-based real-time renderer specifically designed for 3D Gaussian Splatting, allowing users to create photorealistic and navigable 3D scenes from a collection of images. This tool is engineered for efficient rendering on typical graphics hardware, extending the capabilities of point cloud rendering. It provides a robust solution for developers and designers looking to generate immersive 3D environments with high fidelity, making advanced 3D scene creation more accessible and performant. The underlying technology focuses on optimizing the rendering process to deliver smooth, interactive experiences.

EbSynth is a powerful VFX software designed for creative video transformations, retouching, and rotoscopy. It enables users to paint directly into their video by editing individual frames, and then instantly propagates these visual changes across the entire shot. This unique approach allows artists to turn video performances into hand-drawn animations, perform video touch-ups, digital makeup, and colorizing quickly without manual tracking. EbSynth helps users iterate fast and stay immersed in the creative flow by bringing ideas to life instantly. While the core propagation doesn't use AI, an optional AI feature "Generate Image" assists in creating keyframes.