# Fyusion/LLFF

Code release for Local Light Field Fusion at SIGGRAPH 2019

Repository: https://github.com/Fyusion/LLFF
Canonical: https://ross.abutalabs.com/products/llff
Homepage: https://fyusion.com/LLFF
Language: C++
License: GPL-3.0
License Family: copyleft
Topics: light-field, rendering, view-synthesis, deep-learning
Last push: 2023-06-19T14:26:41+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2680, "days_push": 1171, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1703, forks 251 (observed 2026-08-28T04:05:24.489680+00:00)

## What it is
LLFF (Local Light Field Fusion) is a TensorFlow implementation of the SIGGRAPH 2019 paper for novel view synthesis from sparse input images using multi-plane images (MPIs). It includes pretrained models, COLMAP-based camera pose recovery, and Docker-based setup for rendering novel views and videos.

## Use cases
- render novel views of a scene from a few photos
- generate 3D parallax videos from image sets
- recover camera poses with COLMAP and synthesize views
- reproduce Local Light Field Fusion research results
- generate multi-plane images from posed images

## When to avoid
- you need actively maintained code or modern frameworks (PyTorch, recent CUDA)
- you want real-time or production-grade rendering
- you cannot use NVIDIA GPUs with nvidia-docker

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, graphics
- domain: computer-vision, graphics, deep-learning, machine-learning
- platform: python
- tags: view-synthesis, light-field, novel-view-synthesis, multi-plane-images, tensorflow, colmap, siggraph-2019, research-code, linux, docker, gpu

## Member repositories
- Fyusion/LLFF (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.489680+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 2026-08-30T03:37:36.849891+00:00, confidence not recorded.
  - readme: https://github.com/Fyusion/LLFF (fetched 2026-08-28T04:05:24.489680+00:00, sha 62cb916988bc)
  - homepage: https://fyusion.com/LLFF (fetched 2026-08-29T11:12:06.171511+00:00, sha aa71c3debc2d)
  - site_page: https://www.coxautoinc.com/insights/how-ai-is-influencing-vehicle-discovery-and-what-dealers-can-do-about-it (fetched 2026-08-29T11:12:06.179065+00:00, sha 80cc9bd2d9dd)
  - site_page: https://www.coxautoinc.com/insights/what-new-research-reveals-about-ais-growing-role-in-auto-retail (fetched 2026-08-29T11:12:06.180930+00:00, sha 782d1aadf83e)
  - site_page: https://www.coxautoinc.com/about-us (fetched 2026-08-29T11:12:06.174761+00:00, sha a56415a71976)
  - site_page: https://www.coxautoinc.com/press-releases (fetched 2026-08-29T11:12:06.177271+00:00, sha 4f42b30218e0)
- Data as of 2026-08-30T08:39:29.467469+00:00.