Fyusion/LLFF
Code release for Local Light Field Fusion at SIGGRAPH 2019
Implements multi-plane image (MPI) synthesis from sparse input photos using TensorFlow, recovering camera poses via COLMAP structure-from-motion before generating layered scene representations. Blends local light fields across these MPIs to synthesize novel viewpoints, requiring minimal capture data (20-30 handheld images with <64 pixel disparity) and supporting interactive rendering through an OpenGL viewer or video export.
1,693 stars. No commits in the last 6 months.
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"
marrlab/SHAPR_torch
SHAPR: Code for "Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D...
pmh47/dirt
DIRT: a fast differentiable renderer for TensorFlow
natowi/3D-Reconstruction-with-Deep-Learning-Methods
List of projects for 3d reconstruction