# U4D: Unsupervised 4D Dynamic Scene Understanding

arXiv: https://arxiv.org/abs/1907.09905 · HTML: https://mlsanity.com/paper/1907.09905/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

## Built on by (most cited first, 3 of 3)

- [Multi-person Implicit Reconstruction from a Single Image](https://mlsanity.com/paper/2104.09283/) (2021)
- [Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.09259/) (2021)
- [Multi-view data capture for dynamic object reconstruction using handheld augmented reality mobiles](https://mlsanity.com/paper/2103.07883/) (2021)

## Abstract (arXiv)

We introduce the first approach to solve the challenging problem of unsupervised 4D visual scene understanding for complex dynamic scenes with multiple interacting people from multi-view video. Our approach simultaneously estimates a detailed model that includes a per-pixel semantically and temporally coherent reconstruction, together with instance-level segmentation exploiting photo-consistency, semantic and motion information. We further leverage recent advances in 3D pose estimation to constrain the joint semantic instance segmentation and 4D temporally coherent reconstruction. This enables per person semantic instance segmentation of multiple interacting people in complex dynamic scenes. Extensive evaluation of the joint visual scene understanding framework against state-of-the-art methods on challenging indoor and outdoor sequences demonstrates a significant (approx 40%) improvement in semantic segmentation, reconstruction and scene flow accuracy.