MegviiRobot/MegBA

MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment

What it solves

MegBA is designed to handle large-scale Bundle Adjustment (BA), a computationally intensive process used in 3D reconstruction and computer vision. It addresses the slow computation times and memory limitations of existing libraries by leveraging GPU acceleration and distributed computing across multiple GPUs.

Related

  • Project
    blendi-remade/prompt2rig

    prompt2rig turns text prompts into 3D character animations. It uses a video model to generate a clip, then extracts clean 3D body motion (GVHMR) and finger tracking (WiLoR) on your GPU, retargets to Mixamo characters, and exports to Blender or Unity.

  • Project
    blendi-remade/falcraft

    A Minecraft Fabric mod that uses fal.ai to generate 3D structures and live AI video broadcasts directly within the game world from text prompts.

  • Project
    anteloc/ldraw-nova

    An agentic framework that enables AI to design buildable LEGO models by generating Python scripts that produce LDraw 3D CAD source code.

  • Project
    google/xrblocks

    A lightweight, cross-platform library for building AI-integrated XR experiences that works across both specialized headsets and desktop browsers.