[NeurIPS 2024 Spotlight] Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"
Repository Index
142,273 visible repositories in the index
1,009–1,032 of 1,510 · Most stars
A Three.js plugin for Mapbox GL JS, with support for animations and advanced 3D rendering.
- three-js
- mapbox-gl-js
AI-assisted design experiments with documented asset provenance, scoped licensing, and reviewed developer starting points.
- design-system
- frontend
- generative-ui
- glsl-shaders
[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI
- 3d-representation-learning
- foundation-models
- vision-transformers
Python module for hyperspectral image processing
- python
- hyperspectral-image-classification
- hyperspectral
- visualization
one sentence generates any graph
[IROS 2021] BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
- 6dof
- 6d-pose-estimation
- 6dof-pose
- 6dof-tracking
Module to Automatically maximize the utilization of GPU resources in a Kubernetes cluster through real-time dynamic partitioning and elastic quotas - Effortless optimization at its finest!
Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
- human-pose-estimation
- real-time
- 3d-human-pose
- multi-person-pose-estimation
[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
- computer-vision
- computer-graphics
- deep-learning
- 3d-reconstruction
Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agentic, chat, 3D gen, TTS, multimodal, image gen. UnrealMCP/UnrealClaude
Display design token documentation generated from your stylesheets and icon files. Preview design token changes in the browser. Add your design tokens to your Storybook Docs pages using the custom Doc Blocks.
- storybook
- storybook-addon
- design-system
- design-pattern
Your project is scattered across too many tools. Map the chaos on an infinite canvas where notes, files, TO-DOs (and more!) finally live together.
- brainstorming
- collaboration
- idea-management
- mental-space
Fast image loading for React Native backed by performant native libraries.
- image
- nuke
- react-native
- activityindicator
Pure TypeScript image processing that runs everywhere
- image
- image-processing
- image-manipulation
- deno
An AI-powered texture forge for Blender — turn text prompts into seamless PBR materials, concept art and scene-wide projections with local or cloud diffusion models, straight inside the 3D viewport on Windows. · dream textures · dream textures blender · dream textures addon · dream textures ai · dream textures seamless · dream textures pbr
- dream-textures
- dream-textures-addon
- dream-textures-ai
- dream-textures-blender
Draw a pixel-art koi from a GitHub account's public activity, as a looping GIF for a profile README.
- generative-art
- gif
- github-actions
- github-profile
A GPU SVO Builder using rasterization pipeline, a efficient SVO ray marcher and a simple SVO path tracer.
- c-plus-plus
- gpu-svo-builder
- path-tracer
- svo
eepp is an open source, cross-platform C++ GUI framework for building desktop applications, tools, and rich graphical interfaces.
Server-side D3 for static chart/map generation ✨📊
Grand Theft Auto V modding suite for Blender. This add-on allows the creation of modded game assets: 3D models, maps, interiors, animations, etc.
- blender
- blender-addon
- game-modding
- grand-theft-auto
:woman: Library for image processing
- image-processing
- image-manipulation
- canvas
- javascript
Train a state-of-the-art yolov3 object detector from scratch!
- yolov3
- yolo
- object-detection
- python
This layout engine can solve the hardest layout problems imaginable. Its output is DTP grade and deterministic. It's faster than engines written in C++ because it's not traditional. Backed by game engine tech, it has a microkernel and runs a spatial-temporal simulation instead of a giant complex pagination loop.
- canvas
- document
- headless-browser
- layout-engine