Content & Design

MultiTalk is an innovative audio-driven multi-person conversational video generation framework, presented at NeurIPS 2025. It allows users to create videos featuring multiple characters engaging in conversations, singing, and other interactions, all driven by multi-stream audio input. Users provide a reference image and a prompt, and MultiTalk generates a video with consistent lip motions synchronized with the audio. Key features include support for both single and multi-person video generation, interactive character control via prompts, and generalization capabilities for cartoon characters and singing. The tool offers resolution flexibility (480p & 720p) and supports long video generation up to 15 seconds, with ongoing developments for longer durations and enhanced performance.

Vizzio Technologies specializes in creating ultra large-scale 3D reconstructions of digital city models globally, powered by algorithms and AI. Their proprietary "EARTH ENGINE" technology builds dimensionally-accurate, photorealistic, and semantic 3D digital twins of the planet using deep learning and satellite imagery, without the need for drones or LIDAR. This enables timely, global coverage for 3D mapping and visualization. Vizzio's AI can identify building types, extrapolate from imperfect outlines, and reconstruct entire cities. The platform supports cross-platform embedding and offers solutions for immersive virtual tours, real-time digital twins with live video feeds, and enhanced safety, security, and operations management for smart stations and facilities.

Somata Labs, operating under the name Vaivr, offers an advanced AI solution for real-time human mesh generation. This tool can create accurate, production-ready 3D human meshes from a single image or biometric prompt, significantly reducing the time typically spent on manual character creation. Artists maintain creative control while the underlying geometry is handled by deterministic AI, ensuring repeatable results, real-world scalability, and flawless rig integrity. Somata Labs outputs in standard formats like FBX, OBJ, GLB, and USD, making it compatible with leading 3D toolchains such as Unreal and Unity, without requiring conversions, plugins, or manual cleanup. This seamless integration makes it ideal for virtual production workflows.

DataMesh is an industrial digital twin company that leverages Digital Twin and Mixed Reality technologies to empower conventional enterprises. Its FactVerse platform unifies operational data, facility knowledge, and simulation into actionable decisions. The tool offers products like DataMesh Director for creating immersive 3D+XR content, DataMesh Simulator for machinery operations training, and DataMesh Inspector for smart facility management. It supports industrial AI by generating physics-based, photoreal synthetic training data for embodied AI, and provides solutions for real-time monitoring, predictive maintenance, and workflow digitization. DataMesh aims to improve efficiency, reduce risk, and scale intelligent decision-making in complex industrial environments.

Audio-driven-TalkingFace-HeadPose provides PyTorch implementations for generating realistic talking face videos. The tool leverages learning-based personalized head pose prediction, allowing for nuanced and natural head movements synchronized with speech. It supports fine-tuning on short video clips of a target person to personalize the head pose model. Users can then input audio files to generate corresponding talking face videos. The project is based on research papers from Arxiv 2020 and IEEE TMM 2022, and while the code is available for research purposes, commercial use requires contacting the corresponding author.

Hypothetic was a 3D AI and cloud collaboration platform designed to streamline team workflows for creative teams. It offered generative 3D models, real-time sharing, secure access controls, and smart asset management. The platform aimed to boost creativity, productivity, and organization for teams managing 3D and 2D assets. Although it provided various plans including a free individual account with AI generation tokens and storage, the company announced its cessation of operations due to working capital constraints. It was founded in 2021, prior to the mainstream generative AI wave, and focused on cutting-edge technology for 3D asset creation and collaboration.

Alpha3D is an AI-powered platform designed to transform ideas into stunning 3D models instantly. It specializes in text-to-3D and image-to-3D generation, making 3D content creation accessible without requiring specialized skills. The platform enables users to create customizable 3D assets, catering to various applications such as gaming, extended reality (XR), e-commerce, and digital twins. By leveraging AI, Alpha3D simplifies the complex process of 3D modeling, allowing for rapid prototyping and asset generation for diverse creative and commercial needs. Its focus on ease of use and AI-driven capabilities positions it as a valuable tool for both beginners and experienced professionals looking to streamline their 3D workflow.

Autodesk Forma Site Design is a cloud-based, AI-powered software designed for site planning and analysis, primarily targeting architects and design professionals. It enables users to quickly create site and massing models using design automations and understand the full picture of their site earlier with AI-powered analyses. The tool facilitates collaborative design reviews through Forma Board, connecting early design review directly to BIM data. Key features include contextual data setup for geolocated Revit projects, 3D modeling for massing concepts, and environmental analysis to test performance and make data-driven decisions. Forma Site Design integrates with tools like Revit, Rhino, and Dynamo, and supports third-party extensions to enhance design capabilities and streamline workflows.

3DAiLY AI allows users to transform a single photo into a premium 3D model, which can then be turned into jewelry, 3D printed figurines, and other physical keepsakes. The process involves uploading a photo, choosing from 10 unique art styles like Anime or Cyberpunk, and receiving an AI-generated preview within minutes. This preview can be approved or refined. A key differentiator is the "Polished Preview Model" which combines AI generation with human artist cleanup for face/hand/pose correction, clothing refinement, and surface finishing, ensuring print-perfect quality. Users can select from premium materials like Multicolored Premium Resin or Multicolored Sandstone for their physical prints, with various size options available. The tool aims to provide beautiful, high-quality results refined beyond raw AI.

Nilo is a comprehensive game development tool designed to streamline the creation of 3D assets for Roblox. It enables users to generate models from sketches, images, or text prompts, and then refine details, optimize polycount, rig, and animate with ease. The platform supports the creation of custom Roblox-ready avatars and asset packs, allowing users to design entire environments or characters efficiently. Nilo operates entirely in the browser, eliminating the need for complex installations, and offers real-time collaborative playtesting with friends. Users can export their creations with a single click for direct upload to Roblox Studio, making it an accessible solution for both new and experienced builders looking to accelerate their game development workflow.

Meshcapade offers a comprehensive AI toolkit for markerless motion capture, motion generation, and human-understanding. It allows users to capture full body and hand movements with unmatched quality using any camera, from phones to professional setups, without the need for suits or markers. The platform supports various export formats like FBX and GLB, making it compatible with diverse workflows. Built on the SMPL foundation model, Meshcapade's technology adapts to industries such as gaming, fashion, and robotics, providing accurate 3D bodies and motion. It also offers features like realistic 3D hair estimation (coming soon) and is enterprise-proven, privacy-first, and EU/GDPR compliant.

SqueezeSeg is a TensorFlow-based implementation of convolutional neural networks designed for real-time road-object segmentation from 3D LiDAR point clouds. This repository provides the code for SqueezeSeg, a model that processes LiDAR data to identify and segment objects in a scene, crucial for applications like autonomous driving. The project also references SqueezeSegV2, a follow-up work with improved performance, and provides links to download converted datasets for training and validation. It includes instructions for installation, running a demo, and training/evaluating the model, making it a valuable resource for researchers and developers in the field of autonomous vehicles and computer vision.

Talking-Face-Generation-DAVS provides the code for generating talking faces using an Adversarially Disentangled Audio-Visual Representation (DAVS) method, as presented in AAAI 2019. This open-source project allows users to synthesize sequences of face images that correspond to given speech semantics, whether from an unconstrained speech audio or video input. The repository includes scripts for testing, training, and preprocessing data, with support for Python 2.7, PyTorch (version 0.2.0), and OpenCV2. While the current version is primarily for research and educational purposes and may not fully reproduce the paper's results without pretraining, it serves as a valuable reference for implementing talking face generation.

Text2Room is an open-source tool that generates textured 3D meshes of rooms based on a given text prompt. It leverages 2D text-to-image models, specifically Stable Diffusion, to create the 3D structures. The tool is associated with an ICCV 2023 research paper and provides a comprehensive framework for scene generation, including mesh files, renderings, and metadata. Users can customize generation with their own prompts and camera trajectories, or start from an existing image. It also supports optimizing a NeRF for generated scenes, making it valuable for researchers and developers working with 3D content creation and scene understanding.

Text2Tex is an innovative method for generating high-quality textures for 3D meshes directly from text prompts. This tool incorporates inpainting into a pre-trained depth-aware image diffusion model, allowing it to progressively synthesize high-resolution partial textures from multiple viewpoints. To ensure consistency and prevent artifacts, Text2Tex dynamically segments the rendered view into a generation mask, guiding the inpainting process. It also features an automatic view sequence generation scheme to determine the optimal next view for texture updates. Extensive experiments demonstrate its superior performance compared to existing text-driven and GAN-based methods, making it a powerful solution for 3D content creation.

TANGO is an advanced AI tool designed for co-speech gesture video reenactment, leveraging hierarchical audio-motion embedding and diffusion interpolation. This technology allows users to generate videos where a character's gestures are synchronized with an audio input, creating realistic and expressive motion. The tool is presented as an open-source project, making its codebase available for research and development. It includes features for inference, training joint embedding (CLIP), and creating custom gesture graphs. TANGO is particularly useful for researchers and developers in AI-driven video editing and animation, offering a robust framework for generating dynamic, gesture-rich video content from audio.

Movmi is an AI-powered motion capture software designed for 3D animators and game developers. It revolutionizes the animation process by converting 2D video data and descriptive text into high-quality 3D motion capture, eliminating the need for expensive hardware suits. Key features include 'Pose Generate' for transforming text into 3D poses and 'Render AI' for creating videos from captured animations with AI-generated backgrounds. The tool supports multiple human characters in a single scene and offers integration with over 40 Mixamo characters. Movmi provides a collaborative workspace for teams and exports universally accepted FBX files for use in any 3D environment, significantly enhancing efficiency for animators.

UniAnimate is an open-source framework designed to enable efficient and long-term human video generation using unified video diffusion models. It addresses limitations in existing techniques by mapping reference images, posture guidance, and noise video into a common feature space, reducing optimization burden and ensuring temporal coherence. The tool supports a unified noise input for random or first-frame conditioned input, enhancing long-term video generation capabilities. UniAnimate also explores an alternative temporal modeling architecture based on state-space models to replace computation-consuming temporal Transformers, allowing for the generation of highly consistent videos up to one minute in length by iteratively employing a first-frame conditioning strategy. It provides code and models for human image animation, including features for pose alignment and generating video clips at various resolutions.

VividTalk is an open-source project designed for one-shot audio-driven talking head generation. It leverages a 3D hybrid prior to produce realistic facial animations directly from audio input. This tool is particularly suitable for researchers and developers working in AI-driven video synthesis and deepfake creation, offering a foundation for exploring advanced animation techniques. As a GitHub repository, it provides the code and resources for users to implement and experiment with the technology, making it a valuable asset for those interested in the technical aspects of generating dynamic talking head videos.

ArkDesign.AI is an AI-powered design and feasibility study platform specifically tailored for multi-family and mixed-use architectural projects. It enables architects and real estate developers to quickly and efficiently create automated floor plans and comprehensive feasibility reports. The platform is the first AI solution for architectural schematic design, focusing on optimizing profitability, density, and living standards. It incorporates local building codes and ordinances, allowing users to make faster and more informed decisions. ArkDesign.AI is trusted by thousands of users across many countries, having created nearly 100,000 projects, and is recognized for maximizing saleable area and overall efficiency.

PIRender is an open-source tool for controllable portrait image generation, based on the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering." It allows users to synthesize portrait images by intuitively controlling face motions with fully disentangled 3DMM parameters. This model can be applied to various tasks including intuitive portrait image editing, pose and expression alignment, motion imitation, same and cross-identity reenactment, and audio-driven facial reenactment. The project provides source code for PyTorch, detailed installation instructions, and guidance on dataset preparation using VoxCeleb. It also includes scripts for inference, intuitive control, and training, making it a comprehensive resource for researchers and developers in the field of neural rendering.

Cron AI specializes in next-generation 3D perception, leveraging cutting-edge deep learning algorithms to process raw data from 3D sensors such as LiDAR. Their flagship senseEDGE platform provides unparalleled accuracy and intelligence in object detection, classification, and tracking, even in challenging environments and adverse weather conditions. It goes beyond traditional methods, offering adaptive flexibility for seamless object detection across varied settings, geographies, and sensor types. The platform is designed for easy deployment at the edge, scaling effortlessly from single-sensor solutions to complex deployments. Cron AI's technology is crucial for intelligent transportation systems, smart spaces, smart security, and automotive applications, ensuring consistent and precise results while being resource-efficient and GDPR compliant.

Toonapp: AI Photo & Video Art is a mobile application developed by LyrebirdStudio that leverages AI to transform photos into captivating cartoon and video art. Users can easily cartoonify selfies, apply various anime filters, and convert still images into dynamic videos using trendy templates. The app merges powerful AI photo editing software with a beautifully simple design, making it accessible for creative expression. It's available on both iOS and Android platforms, offering a range of tools for personalizing visual content and sharing unique artistic creations.

VirtualWife is a virtual digital human project designed to provide companionship and emotional support. Currently in its incubation phase, the project aims to create a virtual digital human with its own "soul" that users can interact with like a friend. Key features include one-click Docker deployment, support for Linux/Windows/MacOS, customizable character settings, and the ability to change character models from VRM markets. It offers long and short-term memory functions, multi-LLM model switching (including private models like Ollama), and supports text-driven expressions and actions. The tool also integrates with Bilibili for live streaming and enables voice conversations in Chinese, with support for Edge (Microsoft) and Bert-VITS2 voice switching for faster response times through streaming data.