#317 · Primary category： Computer Vision
LLFF
Code release for Local Light Field Fusion at SIGGRAPH 2019
Project last updated：06/19/23
GitHub Stars
1.7K
Forks
251
Contributors
6
License
GPL-3.0
Why we included this project
This TensorFlow release implements the SIGGRAPH 2019 Local Light Field Fusion method, which turns a sparse set of handheld photos into new views of a scene. The workflow is refreshingly direct: you point the scripts at a folder of 20 to 30 casual snapshots, and they recover camera poses with COLMAP, build multi-plane image representations through a pretrained network, and blend them into a rendered video or an interactive OpenGL viewer. Anyone doing 3D capture or photogrammetry around arbitrary real-world scenes will find a clearly documented reference implementation with both Docker and manual installation paths. It also works well as an on-ramp to MPI-based view synthesis before moving on to NeRF-style methods, and the bundled demo lets you confirm the whole flow end to end before processing your own images.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)