zju3dv/Wis3D

A web-based 3D visualization tool for 3D computer vision.

What it solves

Wis3D provides a way for 3D computer vision researchers to visualize complex 3D data directly from Python code. It eliminates the need for manual data conversion or cumbersome tools by allowing users to stream 3D assets into a web browser for real-time inspection.

How it works

Users install the tool and start a web server that hosts the visualization interface. By importing 3D data—such as bounding boxes, point clouds, meshes, and feature correspondences—via Python, the data is sent to the local browser for interactive viewing.

Who it’s for

It is designed for 3D computer vision researchers who need a dedicated tool to inspect and debug 3D spatial data.

Highlights

  • Web-based interface for easy access.
  • Supports 3D bounding boxes, point clouds, and meshes.
  • Visualizes feature correspondences.
  • Integrates directly with Python code.

Related

  • Project
    rendeirolab/LazySlide

    A Python framework for whole slide image analysis that integrates with the scverse ecosystem to enable interoperable and scalable histological workflows.

  • Project
    radekd91/inferno

    A deep learning library for in-the-wild 3D face reconstruction and animation, featuring tools for speech-driven avatars and emotion recognition.

  • Project
    NVIDIA-RTX/RTXNS

    A developer framework for integrating machine learning into graphics applications, enabling the use of neural networks to represent shaders and textures.

  • Project
    Joey-S-Liu/MedSAM3

    A text-guided medical image segmentation model that uses medical concepts to identify and segment targets across diverse modalities without needing bounding boxes or points.