Fyusion/LLFF
Code release for Local Light Field Fusion at SIGGRAPH 2019
This project helps anyone working with 3D scene capture to create smooth, realistic video fly-throughs from a small set of still images. You provide 20-30 handheld photos of a static scene, and it generates a video of the scene from new, unseen camera angles. It's ideal for visual effects artists, architects, real estate agents, or cultural heritage preservationists who need to showcase a space without complex 3D modeling.
1,693 stars. No commits in the last 6 months.
Use this if you need to generate a video touring a static 3D scene using only a few handheld photographs, allowing for flexible camera movement through the captured space.
Not ideal if your scene has moving objects, if you need to capture a very wide area with extreme depth differences between images, or if your input images are not static photographs.
Stars
1,693
Forks
253
Language
C++
License
GPL-3.0
Category
Last pushed
Jun 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Fyusion/LLFF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openspyrit/spyrit
A Python toolbox for deep image reconstruction, with emphasis on single-pixel imaging.
RobotLocomotion/pytorch-dense-correspondence
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"
pmh47/dirt
DIRT: a fast differentiable renderer for TensorFlow
marrlab/SHAPR_torch
SHAPR: Code for "Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D...
natowi/3D-Reconstruction-with-Deep-Learning-Methods
List of projects for 3d reconstruction