# zju3dv/EasyVolcap

[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

Repository: https://github.com/zju3dv/EasyVolcap
Canonical: https://ross.abutalabs.com/products/easyvolcap
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-01-21T08:13:57+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 2, release rhythm 35, longevity 71
- inputs: {"age_days": 1000, "days_push": 589, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1587, forks 99 (observed 2026-08-28T04:05:07.895712+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, graphics, simulation, image-processing, data-science
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python, windows
- tags: volumetric-video, neural-rendering, 4d-reconstruction, novel-view-synthesis, pytorch, cuda, research-framework, multi-view-capture, research, linux, gpu

## Member repositories
- zju3dv/EasyVolcap (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.895712+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:55:26.639532+00:00, confidence not recorded.
  - readme: https://github.com/zju3dv/EasyVolcap (fetched 2026-08-28T04:05:07.895712+00:00, sha aa04982d3461)
- Data as of 2026-08-30T08:39:29.467469+00:00.