Structure from Motion (SfM) and NeRF

Structure from Motion (SfM)

Implemented an end-to end pipeline for Structure from Motion to reconstruct a 3D scene from a set of images and simultaneously obtain the camera poses of the monocular camera with respect to the given scene. Steps involved Feature Matching and Outlier rejection using RANSAC, Estimating Fundamental using epipolar constraint and Essential Matrix, Estimate Camera Pose and Cheirality condition using Triangulation, PnP and Bundle Adjustment.

Input images


Reconstructed scene


Neural Radiance Field (NeRF)

Implemented the modern deep learning approach using Neural Radiance Fields (NeRF) for photo realistic visualization and synthesize novel views of complex scenes.


NeRF using COLMAP

Reconstructed the same scene using COLMAP.


Github repo link

Report link

Contributors: Mihir Deshmukh