# zju3dv/4K4D

[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution

Repository: https://github.com/zju3dv/4K4D
Canonical: https://ross.abutalabs.com/products/4k4d
Homepage: https://zju3dv.github.io/4k4d/
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-06-07T06:30:48+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 75
- inputs: {"age_days": 1051, "days_push": 817, "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 1807, forks 78 (observed 2026-08-28T04:05:39.197852+00:00)

## What it is
4K4D is a research implementation of a 4D point cloud representation for real-time dynamic view synthesis at up to 4K resolution, built on the EasyVolcap volumetric video framework. It renders dynamic 3D scenes at hundreds of FPS using hardware rasterization and includes training and inference code with pretrained models.

## Use cases
- render dynamic 3D scenes in real time from multi-camera video
- train a 4D view synthesis model from RGB video captures
- render free-viewpoint volumetric video at 4K resolution
- reconstruct dynamic humans from multi-view camera rigs
- experiment with differentiable point cloud rasterization

## When to choose
- you need real-time free-viewpoint rendering of dynamic scenes at high resolution
- you have multi-view video captures and want to build a volumetric video
- you want a research baseline for dynamic view synthesis

## When to avoid
- you need a production-ready application rather than research code
- you lack a high-end NVIDIA GPU
- you need simple single-image or static-scene 3D reconstruction

## Facets
- artifact type: library
- maturity: active
- function: graphics, machine-learning, gpu-computing, image-processing
- domain: computer-vision, graphics, deep-learning, machine-learning
- platform: python
- tags: view-synthesis, neural-rendering, 4d-reconstruction, volumetric-video, point-cloud, cvpr-2024, real-time-rendering, cuda-rasterization, gpu, linux

## Member repositories
- zju3dv/4K4D (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:39.197852+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 2026-08-30T03:21:27.646688+00:00, confidence not recorded.
  - readme: https://github.com/zju3dv/4K4D (fetched 2026-08-28T04:05:39.197852+00:00, sha 5585e10cf44f)
  - homepage: https://zju3dv.github.io/4k4d/ (fetched 2026-08-29T11:00:31.331595+00:00, sha 1ff01260659d)
- Data as of 2026-08-30T08:39:29.467469+00:00.