3d-resources

A collection of resources for 3D.
https://github.com/devanshutak25/3d-resources

Last synced: 2 days ago
JSON representation

AI & Machine Learning for CG
- 3D Generation
 - 3DTopia - source text-to-3D pipeline (coarse → refined). See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Open Source | Coarse→Refined · Open Source | Text-to-3D open-source |
 - InstantMesh - image-to-3D reconstruction. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Open Source | Fast · Image→3D | Fast image→3D |
 - Kaedim - to-3D with hybrid AI plus artist cleanup for production quality. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Paid | Hybrid AI+Artist · Production | Production-quality via hybrid AI+artist |
 - Luma Genie - also">See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Freemium | Luma · Integrated | Luma-integrated 3D gen |
 - Meshy v4 - reliable, improved topology and PBR textures. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Freemium | Production-Reliable · PBR | Production-ready AI 3D |
 - Rodin Gen-2 (Hyper3D) - also">See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Freemium | 10B Params · Free Tier | Photorealistic AI 3D |
 - Sloyd - also">See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Freemium | Procedural · Parametric | Parametric procedural 3D |
 - Spline AI - editor. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Freemium | In-Editor · Text→3D | In-editor AI 3D |
 - Stability SPAR3D - source single-image 3D reconstruction. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Open Source | Stability AI · Open Source | Single-image open-source 3D |
 - TRELLIS.2 (Microsoft) - also">See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Open Source | Microsoft · PBR + Open Source | PBR AI 3D (open source) |
 - Tripo v3.0 - level precision, clean quad topology. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Freemium | Clean Quads · Sculpt-level | Clean topology AI 3D |
 - TripoSR - source image-to-3D. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Open Source | Open Source · Fast | Fast open-source image→3D |
 - Unique3D - quality mesh from single image (NeurIPS 2024). See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Open Source | Single-Image · NeurIPS | Single-image open-source 3D |
 - Wonder3D++ - domain diffusion, textured meshes in 2-3min. See also: <a href="#ai-3d-generation-software">Software Reference → AI 3D Generation Software</a> | Open Source | Fast · Textured Mesh | Fast textured mesh gen |
 - Pixal3D - image to 3D asset generation via pixel-feature back-projection. Outputs geometry and PBR textures.
 - Threestudio
- AI-Assisted CG Tools
 - Autodesk Flow Studio (Wonder Dynamics) - also">See also: <a href="#ai-assisted-cg-software">Software Reference → AI-Assisted CG Software</a> | Paid | Auto CG Chars · USD Export | AI CG characters in live plates |
 - Blockade Labs Skybox AI - generated 360° skyboxes/HDRIs from text. See also: <a href="#ai-assisted-cg-software">Software Reference → AI-Assisted CG Software</a> | Freemium | AI Skybox · 360° | AI skyboxes/HDRIs |
 - Gigapixel AI - also">See also: <a href="#ai-assisted-cg-software">Software Reference → AI-Assisted CG Software</a> | Paid | | |
 - Magnific AI - 16x). See also: <a href="#ai-assisted-cg-software">Software Reference → AI-Assisted CG Software</a> | Paid | Creative Upscale · 2-16x | Creative AI upscaling |
 - Rosebud AI - also">See also: <a href="#ai-assisted-cg-software">Software Reference → AI-Assisted CG Software</a> | Freemium | AI Game Builder · Vibe Coding | |
 - Topaz Photo AI / Video AI - in-class upscaling, denoising, sharpening. See also: <a href="#ai-assisted-cg-software">Software Reference → AI-Assisted CG Software</a> | Paid | Upscale · Denoise | Upscale/denoise |
 - Unity Muse - also">See also: <a href="#ai-assisted-cg-software">Software Reference → AI-Assisted CG Software</a> | Paid | Unity AI Suite | |
 - AI Game Developer
 - Comfy UI Blender AI
 - ControlNet
 - Coplay - pill lic-freemium">Freemium. AI Copilot for Unity
 - CorridorKey - driven chroma key for VFX work.
 - CoTracker
 - DEVA (Tracking Anything) - form, multi-object roto with text or click prompts.
 - Dream Textures (Blender)
 - GPT 4 - 4, including tips, applications, limitations, and additional reading materials.
 - RIFE for Nuke - Time Intermediate Flow Estimation for Video Frame Interpolation (ie machine learning for framerate upscaling) for Nuke.
 - Robust Video Matting (RVM) - time human video matting. Strong alpha mattes with no greenscreen.
 - Rotobot - pill lic-paid">Paid. Paid AI roto plugin for Nuke and After Effects. Auto-mattes people and objects.
 - SAM 2 (Segment Anything Model 2)
 - Sammie Roto 2 - based rotoscope app. Click-to-mask, propagates across frames.
 - SolidUI - generated visualization prototyping and editing platform, support 2D, 3D models, combined with LLM(Large Language Model) for quick editing.
 - Track Anything
 - Wonder Studio (Autodesk Flow Studio) - pill lic-freemium">Freemium. AI character replacement with auto roto, body tracking, and re-lighting from a single video. Now part of Autodesk Flow Studio.
- AI Audio & Music
 - ACE Studio - also">See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Freemium | Singing · Expression | AI singing synthesis |
 - AIVA - also">See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Freemium | Orchestral · Scoring | Orchestral/cinematic scoring |
 - DiffRhythm - source full-song gen with vocals from lyrics. See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Open Source | Open Source · Lyrics→Song | Open-source song gen with vocals |
 - ElevenLabs - also">See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Freemium | Voice Cloning · TTS | Voice cloning, TTS |
 - F5 TTS - source zero-shot voice cloning TTS. See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Open Source | Zero-Shot · Voice Clone | Zero-shot voice cloning |
 - Fish Audio - source TTS with voice cloning, fast and multilingual. See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Open Source | Open Source · Multilingual | Open-source TTS |
 - Suno v5 - also">See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Freemium | Song Gen · 100M users | Full song generation |
 - Udio - also">See also: <a href="#ai-audio--music-generation-software">Software Reference → AI Audio & Music Generation Software</a> | Freemium | Electronic/Pop · Commercial | Commercial-licensed AI music |
 - AudioCraft (MusicGen / AudioGen / EnCodec)
- ComfyUI Ecosystem
 - ComfyUI - based AI generator for image/video/3D/audio. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Open Source | Node-based · Multi-modal | Node-based AI workflows |
 - Awesome ComfyUI
 - Comflowy
 - Comfy UI Manager
 - ComfyUI Registry
 - ControlNet SD3.5
- Image Generation
 - Adobe Firefly 3 - safe, deep Creative Cloud integration. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | Commercial-Safe · Adobe CC | Commercial-safe Adobe workflows |
 - Aga Miko/pixel Character Generator - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Open Source | | |
 - Ashawkey/stable Dreamfusion - to-3D dreamfusion, powered by stable diffusion. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Open Source | | |
 - DALL-E 3 (OpenAI) - to-image with strong semantic accuracy. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | OpenAI · Semantic | Semantic accuracy |
 - FLUX 1.1 Pro (Black Forest Labs) - grade open model plus Fill/Canny/Depth tools. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Production-Grade · Open Model | Production-grade image gen |
 - Google Gemini Image Gen - scale production. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Google · Realism | Fast large-scale gen |
 - Grok Aurora (xAI) - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | xAI · Photoreal | Photorealism in Grok |
 - HunyuanDiT (Tencent) - source DiT-based, strong Chinese text. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Open Source | Tencent · DiT | Chinese text rendering |
 - Ideogram 2.0 - in-class typography and text rendering, canvas mode. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Typography · Text Rendering | Typography in images |
 - Jimeng / Dreamina (ByteDance) - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | ByteDance · Video Pipeline | Integrated image + video pipeline |
 - Kolors (Kuaishou) - source, bilingual Chinese/English. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Open Source | Open Source · Bilingual | Bilingual open model |
 - Krea AI - time generation, upscaling, and style transfer platform. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Real-time · Upscaling | Real-time + upscaling |
 - Leonardo AI - time generation with artistic control. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Real-time · Controlled | Controlled artistic generation |
 - Midjourney v7 - leading artistic coherence and stylized output. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | Artistic · Subscription | Artistic and stylized imagery |
 - MusicGen - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Open Source | | |
 - Playground v3 - mode design canvas for graphic design. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Design Canvas · Mixed-mode | Graphic design canvas |
 - Recraft V3 - oriented gen. Vector, icons, brand assets. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Design Focus · Vector | Design assets, vectors |
 - Snowpixel - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | | |
 - Stable Animation SDK - to-animation tool for developers by Stability AI [[dev platform]](https://platform.stability.ai/docs/features/animation) See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | | |
 - Stable Diffusion 3.5 - source diffusion (Large, Medium, Turbo sizes). See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Open Source | Open Source · Self-Host | Self-hosted image gen |
 - UneeQ Digital Humans - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | | |
 - (5) Deforum notebook v0.5 for Stable Diffusion animations is out! Now with math automation, perspective flips, prompt weights, video masking and waifus! : StableDiffusion
 - 3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows - to-image AI in 3D design workflows.
 - AI Render - on renders an AI generated image based on a text prompt and your scene.
 - Canva Adds a Free and Unlimited AI Text-to-Image Generator | PetaPixel - to-Image Generator | PetaPixel.
 - COVAL
 - Deforum Stable Diffusion Animation - v5 Math Functions - Demo and Test - YouTube - v5 Math Functions - Demo and Test - YouTube.
 - Generative AI Genius 2024 (created by Aishwarya Naresh Reganti) course material
 - Introduction to Generative AI Community Course
 - Openai/point E
 - sd-concepts-library (Stable Diffusion concepts library) - browse through objects and styles taught by the community to Stable Diffusion and use them in your prompts!
 - Stable Diffusion Frivolous · Because lawsuits based on ignorance deserve a response
 - Stable Diffusion KLMC2 Animation.ipynb
 - Stable Diffusion KLMC2 Animation.ipynb forked
 - Transforming 2D Images into 3D with the AdaMPI AI Model
 - Word-As-Image for Semantic Typography
- Machine Learning for CG
 - DINOv2 - supervised vision features. Strong general-purpose image embeddings. Useful as backbone for CG ML tasks.
 - IEEE Transactions on Neural Networks and Learning Systems
 - Meta 3D Gen - to-3D. Combines AssetGen geometry with TextureGen materials. Paper and results.
 - PyTorch3D
- Open-Source Models (HuggingFace)
 - Hunyuan Video I2V - to-video, multilingual.
 - SV3D (Stable Video 3D)
- Research Papers
 - Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models - hidden="true">🌐 Project Page](https://research.nvidia.com/labs/toronto-ai/AlignYourGaussians/)
 - Animatable Neural Radiance Fields from Monocular RGB Videos - NeRF) | [bibtex](citations/anim_nerf.txt)
 - BeyondPixels: A Review of the Evolution of Neural Radiance Fields
 - CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations - ops/)] |
 - CLA-NeRF: Category-Level Articulated Neural Radiance Field - nerf.txt)
 - Consolidating Attention Features for Multi-view Image Editing - hidden="true">🌐 Project Page](https://qnerf-consolidation.github.io/qnerf-consolidation/)
 - CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation - NeRF/blob/main/citations/crossfire.txt)
 - Deep Generative Models on 3D Representations: A Survey - hidden="true">🌐 Project Page](https://github.com/justimyhxu/awesome-3D-generation/)
 - DeepCAD: A Deep Generative Network for Computer-Aided Design Models
 - Depth-supervised NeRF: Fewer Views and Faster Training for Free
 - DeRF: Decomposed Radiance Fields - and-Beyond.bib#L222-L228) 
 - Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction - --sun2021direct-->
 - DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images - hidden="true">💻 Code](https://github.com/vLAR-group/DM-NeRF)
 - DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model - hidden="true">🌐 Project Page](https://justimyhxu.github.io/projects/dmv3d/)
 - Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models - hidden="true">🌐 Project Page](https://bluestyle97.github.io/dream3d/) | [💻 Code][Coming soon.]
 - DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior - hidden="true">🌐 Project Page](https://mrtornado24.github.io/DreamCraft3D/) | [💻 Code](https://github.com/deepseek-ai/DreamCraft3D)
 - DreamFusion: Text-to-3D using 2D Diffusion - hidden="true">🌐 Project Page](https://dreamfusion3d.github.io) | [💻 Code](https://github.com/ashawkey/stable-dreamfusion)
 - DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation - hidden="true">🌐 Project Page](https://dreamgaussian.github.io/) | [💻 Code](https://github.com/dreamgaussian/dreamgaussian)
 - DreamGaussian4D: Generative 4D Gaussian Splatting - hidden="true">🌐 Project Page](https://jiawei-ren.github.io/projects/dreamgaussian4d/) | [💻 Code](https://github.com/jiawei-ren/dreamgaussian4d)
 - DreamWaltz: Make a Scene with Complex 3D Animatable Avatars - hidden="true">🌐 Project Page](https://dreamwaltz3d.github.io/) | [💻 Code](https://github.com/IDEA-Research/DreamWaltz)
 - En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data - hidden="true">🌐 Project Page](https://menyifang.github.io/projects/En3D/index.html) | [💻 Code](https://github.com/menyifang/En3D)
 - EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction - hidden="true">🌐 Project Page](https://yifliu3.github.io/EndoGaussian/) | [💻 Code](https://github.com/yifliu3/EndoGaussian)
 - FastNeRF: High-Fidelity Neural Rendering at 200FPS - --Garbin21arxiv_FastNeRF-->
 - From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach - research.github.io/CAD2Program/)] |
 - GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting - hidden="true">🌐 Project Page](https://gala3d.github.io) | [💻 Code](https://github.com/VDIGPKU/GALA3D)
 - GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation - NeRF/blob/main/citations/garf.txt)
 - GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians - hidden="true">🌐 Project Page](https://shenhanqian.github.io/gaussian-avatars)
 - GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting - hidden="true">🌐 Project Page](https://gaussianobject.github.io) | [💻 Code](https://github.com/GaussianObject/GaussianObject)
 - Gemini Robotics 1.5
 - GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields - and-Beyond.bib#L175-L181) 
 - GNeRF: GAN-based Neural Radiance Field without Posed Camera - NeRF/blob/main/citations/gnerf.txt)
 - GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation - hidden="true">🌐 Project Page](https://daipengwa.github.io/GO-NeRF/)
 - GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis - and-Beyond.bib#L237-L243) 
 - GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering - and-Beyond.bib#L291-L297) 
 - IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis - hidden="true">🌐 Project Page](https://mrtornado24.github.io/IDE-3D/) | [💻 Code](https://github.com/MrTornado24/IDE-3D)
 - Image Sculpting: Precise Object Editing with 3D Geometry Control - hidden="true">🌐 Project Page](https://image-sculpting.github.io/) | [💻 Code](https://github.com/vision-x-nyu/image-sculpting)
 - Instant3D: Instant Text-to-3D Generation - hidden="true">🌐 Project Page](https://ming1993li.github.io/Instant3DProj/) | [💻 Code](https://github.com/ming1993li/Instant3DCodes)
 - KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs - --reiser2021kilonerf-->
 - KiloNeuS: Implicit Neural Representations with Real-Time Global Illumination - NeRF/blob/main/citations/kiloneus.txt)
 - Learned Initializations for Optimizing Coordinate-Based Neural Representations - and-Beyond.bib#L268-L274) 
 - Learning the 3D Fauna of the Web - hidden="true">🌐 Project Page](https://kyleleey.github.io/3DFauna/) | [💻 Code]()
 - Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving - SJTU/Lightning-NeRF) | [bibtex](./citations/lightning-nerf.txt)
 - Loc-NeRF: Monte Carlo Localization using Neural Radiance Fields - SPARK/Loc-NeRF) | [bibtex](./citations/locnerf.txt)
 - Local 3D Editing via 3D Distillation of CLIP Knowledge
 - M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts - hidden="true">🌐 Project Page](https://m3dbench.github.io/) | [💻 Code](https://github.com/OpenM3D/M3DBench)
 - Magic3D: High-Resolution Text-to-3D Content Creation - hidden="true">🌐 Project Page](https://research.nvidia.com/labs/dir/magic3d) | [💻 Code][Coming soon.]
 - Make-A-Character: High Quality Text-to-3D Character Generation within Minutes - hidden="true">🌐 Project Page](https://human3daigc.github.io/MACH/) | [💻 Code](https://github.com/Human3DAIGC/Make-A-Character)
 - Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior - hidden="true">🌐 Project Page](https://make-it-3d.github.io) | [💻 Code](https://github.com/junshutang/Make-It-3D)
 - MinD-3D: Reconstruct High-quality 3D objects in Human Brain - hidden="true">🌐 Project Page](https://jianxgao.github.io/MinD-3D/) | [💻 Code](https://github.com/JianxGao/MinD-3D)
 - Mixture of Volumetric Primitives for Efficient Neural Rendering
 - NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes - irshad/NeO-360) | [bibtex](./citations/SurfelNeRF.txt)
 - NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields - mae.txt)
 - NeRF-VAE: A Geometry Aware 3D Scene Generative Model - vae.txt)
 - NeRF: Neural Radiance Field in 3D Vision, Introduction and Review
 - NeRF++: Analyzing and Improving Neural Radiance Fields - 46/nerfplusplus) | [bibtex](./NeRF-and-Beyond.bib#L345-L351) 
 - Neural Volume Rendering: NeRF - Chen, Arxiv 2020 | [blog](https://dellaert.github.io/NeRF/) | [github](https://raw.githubusercontent.com/yenchenlin/awesome-NeRF/main/NeRF-and-Beyond.bib) |
 - NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
 - One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion - hidden="true">🌐 Project Page](https://sudo-ai-3d.github.io/One2345plus_page/) | [💻 Code](https://github.com/SUDO-AI-3D/One2345plus)
 - ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds - codebase)] |
 - PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
 - pixelNeRF: Neural Radiance Fields from One or Few Images - nerf) | [bibtex](./NeRF-and-Beyond.bib#L329-L335) 
 - PlankAssembly: 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs - research.github.io/PlankAssembly/)] [[code](https://github.com/manycore-research/PlankAssembly/)] |
 - Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders
 - PolyGen: An Autoregressive Generative Model of 3D Meshes - research/blob/master/polygen/)] |
 - PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
 - Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts - hidden="true">🌐 Project Page](https://cxh0519.github.io/projects/Progressive3D/) | [💻 Code](https://github.com/cxh0519/Progressive3D)
 - PSAvatar: A Point-based Shape Model for Real-Time Head Avatar Animation with 3D Gaussian Splatting - hidden="true">💻 Code](https://github.com/pcl3dv/PSAvatar)
 - PVDeconv: Point-voxel deconvolution for autoencoding cad construction in 3D - dataset/)] |
 - Reconstructing Editable Prismatic CAD from Rounded Voxel Models
 - RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D - hidden="true">🌐 Project Page](https://aigc3d.github.io/richdreamer/) | [💻 Code](https://github.com/modelscope/richdreamer)
 - Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos - hidden="true">🌐 Project Page](http://shahrukhathar.github.io/2024/02/05/Rig3DGS.html)
 - RT-NeRF: Real-Time On-Device Neural Radiance Fields Towards Immersive AR/VR Rendering - nerf.txt)
 - SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance - hidden="true">🌐 Project Page](https://seeavatar3d.github.io/)
 - SIGNeRF: Scene Integrated Generation for Neural Radiance Fields - hidden="true">🌐 Project Page](https://signerf.jdihlmann.com/) | [💻 Code](https://github.com/cgtuebingen/SIGNeRF)
 - Streaming Radiance Fields for 3D Video Synthesis
 - Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting - hidden="true">🌐 Project Page](https://zju3dv.github.io/street_gaussians/) | [💻 Code](https://github.com/zju3dv/street_gaussians)
 - Supervised Fitting of Geometric Primitives to 3D Point Clouds
 - SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes - web/) | [bibtex](./citations/SurfelNeRF.txt)
 - Taming Mode Collapse in Score Distillation for Text-to-3D Generation - hidden="true">🌐 Project Page](https://vita-group.github.io/3D-Mode-Collapse/) | [💻 Code](https://github.com/VITA-Group/3D-Mode-Collapse)
 - Text-To-4D Dynamic Scene Generation - hidden="true">🌐 Project Page](https://make-a-video3d.github.io)
 - Text2CAD: Text to 3D CAD Generation via Technical Drawings - project/)] |
 - TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields - hidden="true">🌐 Project Page](https://tyhuang0428.github.io/textfield3d.html)
 - TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion - hidden="true">🌐 Project Page](https://texturedreamer.github.io/)
 - TOSS:High-quality Text-guided Novel View Synthesis from a Single Image - hidden="true">🌐 Project Page](https://toss3d.github.io/)
 - Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers - hidden="true">🌐 Project Page](https://zouzx.github.io/TriplaneGaussian/)
 - ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields - hidden="true">💻 Code](https://github.com/Dongjiahua/VICA-NeRF)
 - Volume Rendering of Neural Implicit Surfaces
 - Wonder3D: Single Image to 3D using Cross-Domain Diffusion - hidden="true">🌐 Project Page](https://www.xxlong.site/Wonder3D/) | [💻 Code](https://github.com/xxlong0/Wonder3D)
 - X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360° Insufficient RGB-D Views - nerf.txt)
 - Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model - hidden="true">🌐 Project Page](https://zero123.cs.columbia.edu/) | [💻 Code](https://github.com/SUDO-AI-3D/zero123plus) | [🤗 Hugging Face](https://huggingface.co/spaces/sudo-ai/zero123plus-demo-space)
- Texture & Material Generation
 - Adobe Firefly Textures - to-edit texture workflows. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | Adobe · Prompt-to-Edit | Adobe-integrated AI textures |
 - InstaMAT - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | Substance-alt · AI Workflows | AI-assisted material authoring |
 - Meshy Textures - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Meshy Pipeline · Integrated | Textures tied to Meshy 3D |
 - Ponzu - also">See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Freemium | Mesh-aware · Text→Tex | Mesh-aware AI textures |
 - Scenario - ready PBR materials, full map sets. See also: <a href="#ai-image--texture-generation-software">Software Reference → AI Image & Texture Generation Software</a> | Paid | Game-Ready · Full Maps | Game-ready AI materials |
- Video Generation
 - Cog Video X - source, multiple sizes. See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Open Source | Open Source · Tsinghua | Research open-source video gen |
 - Genmo Mochi 1 - source video gen model. See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Open Source | Open Source · Genmo | Open-source video gen |
 - Hailuo AI / MiniMax - also">See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Freemium | Director Model · Character Consist | Directed motion |
 - Haiper - DeepMind team, animation and video-to-video modes. See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Freemium | Ex-DeepMind · V2V | Video-to-video |
 - HunyuanVideo 1.5 - source 8.3B params, runs on 14GB VRAM. See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Open Source | Open Source · 14GB VRAM | Self-hosted video gen |
 - Kling 3.0 - also">See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Freemium | 5min Clips · Motion Brush | Long clips, human motion |
 - LTX Video - source, real-time generation speeds. See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Open Source | Open Source · Real-time | Real-time open-source video gen |
 - Luma Dream Machine - also">See also: <a href="#ai-video-generation-software">Software Reference → AI Video Generation Software</a> | Freemium | Fast · Camera Motion | Fast video gen |

Programming Languages

C# 243 Python 150 C++ 143 JavaScript 13 C 9 HTML 8 Jupyter Notebook 8 ShaderLab 8 TypeScript 6 GDScript 6

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

3d-resources

AI & Machine Learning for CG

3D Generation

AI-Assisted CG Tools

AI Audio & Music

ComfyUI Ecosystem

Image Generation

Machine Learning for CG

Open-Source Models (HuggingFace)

Research Papers

Texture & Material Generation

Video Generation