Lists (28)
3D LLM
3D LLM staff3D Reconstruction
Agent
AIGC-2D
text to image, text to video, etc.AutoRig
Blender
blender tools, tutorialsDataset
datasetDifferentiableRendering
Differentiable Rendering, for texture backing, mesh decimation etc.DigitalHuman3D
3D Digital HumanFoundation Models
Vision foundational models, building blocksFunnyThings
interesting things, learningImg2Img
Image to Image Generation | TranslationLLM/VLM
Pure text large language model or visual large language modelMaya
Mesh Decimation & Processing
Mesh Decimation (edge collapse or remesh based methods)Mesh Segmentation
algorithms about mesh segmentationsMeshGen & TexGen
Auto Regressive based mesh generation | Texture GenerationMISC 3DV
MotionCap
WholeBody/Body/Hand/Head 2D Pose Estimation / 3D Pose Estimation / Motion Capture from RGB image / videoMulti-modal 3D Shape Retrieval
NVS
PI
Primitive Fitting, 3D Assembly
Fit a complicated 3D model (mesh / point cloud) with several predefined 3D primitivesSurvey
TalkingHead
Text/Image to 3D
Text to 3D / Image to 3D Generation models | SDS | LRM | SOTAUtilities
Libraries, frameworks, useful toolsVirtualAvatar
Stars
SVBRDF estimation from photographs for three different lighting conditions (directional, natural, and flash/no-flash illumination) is shown by refining a novel SVBRDF diffusion backbone model.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
DataTool is a program that lets you extract models, maps, and files from Overwatch.
Open Source framework for voice and multimodal conversational AI
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
Fast and local neural text-to-speech engine
[SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes
🐧 在 Linux 上提供一套完整的 Clash / Mihomo（Clash Meta） 代理与管理面板
A simple 3D asset retrieval system based on objaverse. Query any 3D asset using text(CN/EN) or images, inter-modal or cross-modal. Equipped with backend API service and front-end gradio demo.
Miro: Conversational and editable 3D asset generation from text and images
Turn detection for full-duplex dialogue communication
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Maya-ACE: A Reference Client Implementation for NVIDIA ACE Audio2Face Service
Orient Anything V2, NeurIPS 2025 Spotlight
Harness the power of NVIDIA technologies and LangChain to create dynamic avatars from live speech, integrating RIVA ASR and TTS with Audio2Face for real-time, expressive digital interactions.