zju3dv/EasyVolcap

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1594 stars · 100 forks observed · 2026-10-05

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

EasyVolcap is a PyTorch-based library for accelerating neural volumetric video research, covering volumetric video capture, reconstruction, and rendering. It was presented at SIGGRAPH Asia 2023 and underpins the real-time 4D view synthesis algorithm 4K4D.

Use cases

• reconstruct volumetric video from multi-view camera captures
• train neural volumetric video models in PyTorch
• render free-viewpoint 4D video in real time
• build novel view synthesis research prototypes
• run a local viewer for volumetric video results
• develop CUDA-accelerated rendering extensions for neural graphics

When to choose

• you are doing research on neural volumetric video or 4D reconstruction
• you need a ready-made pipeline for multi-view capture to rendering
• you want to reproduce or extend 4K4D-style real-time view synthesis
• you work with CUDA and PyTorch on GPU workstations

When to avoid

• you need a polished end-user application rather than a research codebase
• you have no GPU or CUDA build environment available
• your project is simple 2D image or video processing unrelated to volumetric capture
• you require a permissive license for commercial use, since the license is custom (zju3dv)

Facets

library · maturity active

machine-learning deep-learning graphics simulation image-processing data-science computer-vision graphics machine-learning deep-learning python windows volumetric-video neural-rendering 4d-reconstruction novel-view-synthesis pytorch cuda research-framework multi-view-capture research linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zju3dv/EasyVolcap")