# Temporally Coherent General Dynamic Scene Reconstruction

arXiv: https://arxiv.org/abs/1907.08195 · HTML: https://mlsanity.com/paper/1907.08195/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2019.

## Built on by (most cited first, 6 of 6)

- [Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactions](https://mlsanity.com/paper/2108.00362/) (2021)
- [The One Where They Reconstructed 3D Humans and Environments in TV Shows](https://mlsanity.com/paper/2207.14279/) (2022)
- [Panoptic Segmentation: A Review](https://mlsanity.com/paper/2111.10250/) (2021)
- [Multi-view data capture for dynamic object reconstruction using handheld augmented reality mobiles](https://mlsanity.com/paper/2103.07883/) (2021)
- [Dynamic Scene Novel View Synthesis via Deferred Spatio-temporal Consistency](https://mlsanity.com/paper/2109.01018/) (2021)
- [4D Vessel Reconstruction for Benchtop Thrombectomy Analysis](https://mlsanity.com/paper/2604.06671/) (2026)

## Abstract (arXiv)

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.