# Temporally Coherent General Dynamic Scene Reconstruction

## TL;DR

This paper presents a novel method for 4D dynamic scene reconstruction from multiple wide-baseline cameras, achieving improved accuracy and temporal coherence without prior scene knowledge, enabling applications like free-viewpoint rendering.

## Contribution

It introduces an automatic coarse reconstruction, temporal correspondence with joint segmentation, and a robust shape-constrained refinement approach for dynamic scenes.

## Key findings

- Improved multi-view segmentation accuracy
- Enhanced dense reconstruction quality
- Effective 4D scene modeling for VR applications

## Abstract

Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a general approach to obtain a 4D representation of complex dynamic scenes from multi-view wide-baseline static or moving cameras without prior knowledge of the scene structure, appearance, or illumination. Contributions of the work are: An automatic method for initial coarse reconstruction to initialize joint estimation; Sparse-to-dense temporal correspondence integrated with joint multi-view segmentation and reconstruction to introduce temporal coherence; and a general robust approach for joint segmentation refinement and dense reconstruction of dynamic scenes by introducing shape constraint. Comparison with state-of-the-art approaches on a variety of complex indoor and outdoor scenes, demonstrates improved accuracy in both multi-view segmentation and dense reconstruction. This paper demonstrates unsupervised reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction and its application to free-viewpoint rendering and virtual reality.