# Probabilistic Dense Reconstruction from a Moving Camera

## TL;DR

This paper introduces a probabilistic method for real-time dense 3D reconstruction from a moving monocular camera, leveraging spatial and temporal correlations to improve depth estimation accuracy and robustness.

## Contribution

It proposes a novel online recursive probabilistic scheme that integrates depth estimates with covariances and inlier probabilities into dense 3D models, enhancing monocular reconstruction.

## Key findings

- Outperforms state-of-the-art methods in TUM RGB-D SLAM and ICL-NUIM datasets.
- Demonstrates effectiveness in both indoor and outdoor real-time experiments.
- Improves robustness and accuracy of monocular dense reconstruction.

## Abstract

This paper presents a probabilistic approach for online dense reconstruction using a single monocular camera moving through the environment. Compared to spatial stereo, depth estimation from motion stereo is challenging due to insufficient parallaxes, visual scale changes, pose errors, etc. We utilize both the spatial and temporal correlations of consecutive depth estimates to increase the robustness and accuracy of monocular depth estimation. An online, recursive, probabilistic scheme to compute depth estimates, with corresponding covariances and inlier probability expectations, is proposed in this work. We integrate the obtained depth hypotheses into dense 3D models in an uncertainty-aware way. We show the effectiveness and efficiency of our proposed approach by comparing it with state-of-the-art methods in the TUM RGB-D SLAM and ICL-NUIM dataset. Online indoor and outdoor experiments are also presented for performance demonstration.