Content & Design

nerf2mesh is an open-source PyTorch re-implementation of the paper "Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement." This tool excels at extracting high-quality, textured 3D meshes from Neural Radiance Fields (NeRF) representations. It offers advanced features like background removal and an SDF (Signed Distance Function) mode for stage 0 processing, which significantly enhances the robustness and smoothness of meshes, particularly for single-object reconstructions. Users can refine meshes with adaptive surface refinement, control decimation targets, and adjust parameters for surface quality versus rendering quality. It supports both original NeRF data formats and COLMAP datasets, making it versatile for various 3D reconstruction tasks.

Tripo AI is a leading online 3D model generator that transforms concepts into lifelike 3D creations in seconds. It enables users to generate high-quality 3D models from text prompts or images, featuring sharp geometry and solid topology. The platform offers intelligent segmentation to split complex models into editable parts, AI texturing with one-click application and a Magic Brush for detailed control, and automatic rigging and animation for static meshes. Tripo AI significantly reduces the time and effort typically required for 3D modeling, making it accessible for various creative industries including gaming, 3D printing, animation, and product design. It also provides a Gamehub for exploring AI-generated 3D games and an API for developers.

Protein Structure Modeling is an AI tool available on Hugging Face Spaces, designed for predicting and visualizing protein structures. This application is particularly useful for researchers and students in fields such as biology, biochemistry, and pharmacology, who require accurate structural models for their work. While the current live website indicates a runtime error, suggesting temporary unavailability, the tool's core purpose is to facilitate scientific research and educational endeavors by providing a platform for protein structure analysis. Its integration within the Hugging Face ecosystem implies a focus on accessibility and community-driven development in AI-powered scientific tools.

ls graphicsVerified is a comprehensive platform offering a vast collection of high-quality mockups for graphic and UI designers. It provides both free and premium mockups compatible with Photoshop and Figma. The tool allows users to enhance their design projects with a wide array of device and packaging mockups, including environment, isolated, longscroll, and animated mockups. Beyond static images, ls.graphics also features online tools like a Figma mockup plugin and ColorFlow, a free gradient mesh generator. Users can edit mockups directly in their browser or within Figma, with options to download PSD, Sketch, and Figma files for full access subscribers. The platform caters to designers seeking professional and consistent mockups for portfolios, brand guidelines, and various design presentations.

svox2 is an open-source project that implements Plenoxels, a technique for representing radiance fields without relying on neural networks. This approach offers an alternative to traditional neural radiance fields for 3D scene representation and rendering. The tool is designed for researchers and developers in computer vision and 3D graphics, providing official optimization code and support for various dataset formats like NeRF-Blender, LLFF, NSVF, and CO3D. It includes scripts for data processing, optimization, and rendering, with options for single scene training or parallel task execution. While primarily tested on Linux, it offers a robust framework for experimenting with radiance fields.

In3D enables users to create realistic full-body 3D avatars quickly using just a phone camera. These avatars are suitable for integration into metaverses, games, and other applications. The platform provides an SDK for Unreal Engine and Unity, allowing developers to easily incorporate in3D avatars into their products. Users can also explore the quality of their 3D models and export them in formats like FBX, GLB, or USDZ. In3D aims to personalize user experiences with its realistic and customizable avatar technology.

Genie 3 World is a revolutionary AI tool powered by DeepMind's world model technology, enabling users to generate immersive 3D virtual environments from simple text prompts. It offers real-time interaction, allowing users to explore, modify, and interact within these generated worlds. The platform boasts advanced features such as accurate physics simulation, dynamic weather, and responsive AI characters, making it ideal for diverse applications including robot training, educational simulations, and entertainment. Users can navigate worlds with keyboard controls, modify environments with text commands, and benefit from professional-grade visual fidelity and spatial coherence. Genie 3 World aims to simplify complex 3D environment creation, saving significant development hours for professionals.

Stable Virtual Camera (SEVA) is an advanced open-source AI tool developed by Stability AI and University of Oxford for Novel View Synthesis (NVS). It leverages generalist diffusion models to generate 3D consistent novel views of a scene, requiring only a few input views and target camera configurations. The tool is designed for researchers and power users, offering both a user-friendly Gradio GUI demo and a command-line interface (CLI) for fine-grained control. It supports Python 3.10+ and Torch 2.6.0+, with model weights available via Hugging Face. SEVA is ideal for academic research and development in virtual camera applications, providing a robust framework for exploring generative view synthesis.

Animated Drawings by Meta AI Research is an innovative tool designed to transform static sketches into dynamic animations. This platform enables users to bring their drawings, particularly children's artwork, to life by animating characters to move and interact. The tool emphasizes an easy-to-use interface, making the animation process accessible to a broad audience without requiring advanced technical skills. It fosters creativity and imagination by providing a simple yet powerful way to visualize static art in motion. The focus on user privacy and safety ensures a secure environment for creative exploration. This tool is ideal for anyone looking to add a playful and interactive dimension to their drawings, making it a valuable resource for parents, educators, and creative individuals.

Artdott specializes in designing immersive brand experiences and digital art installations, transforming physical spaces into engaging and memorable moments. The platform offers services including creative direction, artist IP licensing, and bespoke immersive installations for both physical and digital environments. Artdott helps brands, cultural venues, and global events to enhance engagement, particularly with Gen Z and Millennial audiences, through spatial storytelling and unique digital art. They provide access to a curated selection of Artdott Artists' IP for spatial activations and custom-designed installations tailored to specific spaces and brands.

Avatalks provides an innovative AI language learning experience through interactive 3D avatar tutors. The platform is designed to help users build vocabulary, master grammar, and achieve fluency by engaging in real conversations. It features a structured Learn Section for foundational knowledge, covering vocabulary, grammar, listening, and reading exercises. Additionally, the Chat Section utilizes AI to simulate real-life conversation practice, allowing users to apply what they've learned. Avatalks offers progress insights, the ability to save unlimited favorite words, and tools for pronunciation and writing. Users can learn multiple languages under one account, with progress saved for each, making it a versatile tool for language enthusiasts.

EmemeAI provides a platform for generating and engaging with personalized 3D AI characters. Users can create unique AI personalities and interact with them through real-time conversations. A key feature is the automatic generation of animations based on the context of the conversation, bringing the characters to life dynamically. The platform also supports exporting these AI characters to external environments such as VRChat, making them versatile for various applications. This tool is designed to simplify the process of character creation and interaction, offering an intuitive experience for users interested in virtual character development and immersive digital experiences.

PyTorch3D is FAIR's open-source library designed to provide efficient and reusable components for deep learning with 3D data, specifically within the PyTorch framework. It offers key features such as data structures for storing and manipulating triangle meshes, along with efficient operations like projective transformations, graph convolution, and sampling. A notable component is its differentiable mesh renderer, which is crucial for integrating 3D data into deep learning pipelines. The library is built to handle minibatches of heterogeneous data, can be differentiated, and utilizes GPUs for acceleration, making it suitable for advanced 3D computer vision research and applications like Mesh R-CNN.

stable-dreamfusion is an open-source PyTorch implementation of the Dreamfusion text-to-3D model, leveraging the Stable Diffusion text-to-2D model. It facilitates the creation of 3D content from both text prompts and images, offering mesh exportation capabilities using NeRF and diffusion techniques. The project is actively developed and includes features like support for Perp-Neg to address multi-head problems in text-to-3D, compatibility with Stable Diffusion and DeepFloyd-IF, and the use of multi-resolution grid encoders for faster rendering. Users can choose between Instant-NGP or Vanilla NeRF backbones, and it supports DMTet finetuning for higher resolution meshes. It also allows for image-conditioned 3D generation using Zero-1-to-3.

AMGI Studios is an independent animation technology and gaming company that lives at the intersection of AI technology, gaming, and the magic of storytelling. They specialize in character-driven AI, creating dynamic, lifelike interactions that evolve based on user input. Leveraging sophisticated natural language and vision processing, as well as emotional intelligence, their AI characters understand and respond to human emotions, making each interaction personalized and immersive. Founded on real-time animation workflows, AMGI Studios delivers high-quality animated content with significantly reduced production time and costs. They also craft innovative, secure, and engaging games, and are leaders in Web3, integrating blockchain technology for decentralized, player-owned experiences.

Artflow AI is an innovative AI photography studio designed to transform users into diverse characters within any setting and wearing any outfit. This comprehensive toolkit caters to artists, storytellers, and creators, offering features like Character Builder, Image Studio, Video Studio, and Story Studio. Users can effortlessly create and animate characters, generate high-quality images, and craft compelling narratives. A standout feature is the Actor Builder, which allows for instant character creation by simply uploading images. Artflow AI streamlines the creative process, enabling users to explore their imagination without technical barriers, making it ideal for visual content creation and character-driven projects.

nerf_pl provides an unofficial implementation of NeRF (Neural Radiance Fields) and NeRF in the Wild, built with pytorch-lightning. This project focuses on offering a simpler and faster training procedure compared to official implementations, with detailed comments to aid understanding. It supports multi-GPU training, significantly reducing processing time for synthetic datasets. Key features include the ability to reconstruct colored meshes, integrate with game engines like Unity for mixed reality and real-time volume rendering, and create portable scenes. The tool also includes an improved NSFF implementation for handling dynamic scenes and offers Colab notebooks for easy usage without GPU requirements.

Scenario offers a comprehensive creative AI infrastructure designed to generate on-brand assets across image, video, audio, and 3D. Users can train custom AI models using their own art bible and style references, ensuring every generated asset aligns with their unique creative DNA. The platform provides access to over 500 models from 50+ providers, keeping creative teams updated with the latest AI advancements. Scenario also features a visual node-based workflow builder for creating multi-step pipelines and agents for batch generation, API integration, and team collaboration. It's built for enterprise-grade security, compliance, and scalability, making it suitable for various industries including gaming, marketing, e-commerce, and film.

Draw Cartoons 2: Learn&Animate is an Android mobile application designed for creating animated movies and cartoons. The app simplifies the animation process, making it accessible for both beginners and experienced animators. It incorporates features such as skeletal animation and motion tweening, which allow for smooth character movements without the need to draw every single frame. This approach significantly reduces the time and effort typically required in traditional animation, enabling users to focus more on storytelling and creative expression. The tool aims to provide a user-friendly platform for bringing animated ideas to life directly from a mobile device.

Toppy, rebranded as Fmly, is a comprehensive parental control application designed to help parents ensure their children's online safety and physical whereabouts. The app allows real-time GPS location tracking, monitoring of contact lists, and setting up geo-fences to receive alerts when a child enters or leaves specific areas. For Android devices, it extends capabilities to include monitoring installed apps, surrounding audio recording, and remote camera access. Parents can also utilize a panic button feature for emergencies. The app requires installation on both the parent's and child's phones, with a straightforward setup process. It provides detailed instructions for managing permissions and troubleshooting common issues like location updates or subscription cancellations.

uSens Inc. is a Silicon Valley startup founded in 2014, specializing in interactive computer-vision tracking and XR headset solutions. The company's technology transforms human-computer interaction through AI-based methods, including fast and precise 3D hand skeleton tracking compatible with RGB, gray, and depth cameras. uSens also offers comprehensive XR SLAM and hand tracking solutions for AR, MR, and mobile applications, providing immersive and interactive experiences. Beyond XR, uSens develops Vehicle HMI solutions featuring DMS, free-hand interaction, head tracking, and gaze tracking. With over 30 patents and experience across more than 10 domains including VR, AR, smartphones, cars, robotics, and medical, uSens provides a full suite of hardware, optics, camera systems, VST, and VR rendering systems.

Lummi offers a diverse collection of free AI-generated stock images, illustrations, and 3D visuals, designed to enhance various creative projects. The platform provides royalty-free assets, ensuring users can incorporate them into their designs without licensing concerns. Each image is created by a global network of digital artists, blending human creativity with AI capabilities. Lummi aims to provide high-quality visual content that helps users avoid generic or 'boring' design, making it suitable for presentations, websites, social media, and other visual communication needs. The tool emphasizes unique and distinctive visuals to elevate creative output.

DRESSX is the world's leading platform for AI, AR, and avatar fashion technologies, offering a comprehensive suite of products for both individuals and businesses. For brands, DRESSX provides an AI Suite with tailored solutions for fashion commerce, including an AI-driven Virtual Try-On that boosts customer confidence and reduces return rates by up to 75%. They also specialize in crafting high-quality game avatars, skins, wearables, and cosmetics, serving as an official vendor for industry giants like Meta and Snap/Bitmoji. For individuals, DRESSX allows users to wear digital fashion in AR, with AI, and on their avatars. The platform aims to revolutionize how fashion is consumed and experienced in the digital realm.

Arrea is a digital product engineering company focused on building the next generation of web and app experiences. They specialize in creating scalable, intelligent, and future-ready platforms, including AI-driven interfaces and ultra-responsive mobile applications. Their work encompasses diverse projects such as developing a HIPAA-compliant web platform for online radiology second opinions, creating a comprehensive database of radiology reports, and aggregating radiology news. Arrea also offers consumer-facing AI tools like an AI Kids Portrait Generator and an Augmented Reality (AR) app for creative exploration.