Search

Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.

Konva.js is an HTML5 Canvas JavaScript framework for interactive graphics, design editors, whiteboards, and diagrams. Scene graph with events, drag and drop, transforms, animations, and export.

Universal Scene Description

Code repository for "TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"

:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

Baldur's Gate: Enhanced Edition Trilogy (EET) is a modification for Baldur's Gate II: Enhanced Edition that merges whole saga into one game and provides continuity between the events of Baldur's Gate, Tales of the Sword Coast, Shadows of Amn, Throne of Bhaal and Siege of Dragonspear expansion (also for both Black Pits adventures). The name of this this modification probably rings a bell to those who have been following IE modding scene, thanks to the classic mod that inspired this project, called Baldur's Gate Trilogy (BGT), developed by Bardez and Ascension64. While EET remains mostly faithful to the premise of the BGT, it shouldn't be considered a direct continuation of that project. In fact both mods share little to no common code and took different design decisions in many aspects.

Immediate mode 3D gizmo for scene editing and other controls based on Dear Imgui

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

A common USD (Universal Scene Description) plugin for Autodesk Maya

Vulkan ray tracing glTF 2.0 renderer — RTX path tracer with PBR materials, AI denoising (DLSS, OptiX), and scene editing. NVIDIA open-source sample.

CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包

This repo accompanies the research paper, ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data and contains the data, scripts to visualize and process assets, and training code described in our paper.

NVIDIA-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox

Official C# implementation of GDUnit4 - a comprehensive unit testing framework for Godot 4. Features VS/Rider test adapter integration, parameterized tests, scene runners, and extensive assertion methods.

A drop-in replacement for the wlroots scene API that allows wayland compositors to render surfaces with eye-candy effects

A staging area for the scene system

[CVPR'24] GraphDreamer: a novel framework of generating compositional 3D scenes from scene graphs.

Godot template with a main menu, options menus, credits, and a scene loader.

This repo contains a curative list of scene change detection(SCD), including papers, videos, codes, and related websites.

[ICCV 2025] GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene

Give your AI assistant eyes and hands in the Godot editor: scene editing, input injection, deterministic playtesting, and live game state for agents

CorbeauSplat is an all-in-one Gaussian Splatting automation tool designed specifically for macOS Silicon. It streamlines the entire workflow from raw video/images to a fully trained and viewable 3D scene (Gaussian Splat).

GoPeak — The most comprehensive MCP server for Godot Engine. 95+ tools: scene management, GDScript LSP, DAP debugger, screenshot capture, input injection, ClassDB introspection, CC0 asset library. npx gopeak

A Bevy 0.19 scene editor with hierarchy, inspector, and 3D viewport

Unity MCP Server — 268 tools for AI-assisted game development. Connect Claude, Cursor, or any MCP client to Unity Editor & Unity Hub. Scene management, GameObjects, components, builds, profiling, Shader Graph, Amplify, terrain, physics, NavMesh, animation, MPPM multiplayer & more. Free & open source by AnkleBreaker Studio.

Local-first desktop AI: chat with your files, turn one line into a living 3D scene, investigate logs and harden configs. Runs on your laptop, works offline.

Official code of "Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding"

[ ECCV 2026 ] Seen2Scene takes an incomplete real-world 3D scan and generates a complete, coherent 3D scene using visibility-guided flow matching — trained directly on real-world data.

Flowboard — open-source infinite canvas for AI product videos. Drag nodes for model, product, scene, video — connect them, click Generate. Auto-prompts write themselves. Runs locally; powered by Google Flow + Claude CLI.

Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding (ECCV 2026 Long Oral)