# Multiframe Scene Flow with Piecewise Rigid Motion

arXiv: https://arxiv.org/abs/1710.02124 · HTML: https://mlsanity.com/paper/1710.02124/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2017.

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

- [Weakly Supervised Learning of Rigid 3D Scene Flow](https://mlsanity.com/paper/2102.08945/) (2021)
- [Self-Supervised Multi-Frame Monocular Scene Flow](https://mlsanity.com/paper/2105.02216/) (2021)
- [M-FUSE: Multi-frame Fusion for Scene Flow Estimation](https://mlsanity.com/paper/2207.05704/) (2022)
- [Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds](https://mlsanity.com/paper/2104.04724/) (2021)
- [Self-Supervised Multi-Frame Neural Scene Flow](https://mlsanity.com/paper/2403.16116/) (2024)
- [SSF-PAN: Semantic Scene Flow-Based Perception for Autonomous Navigation in Traffic Scenarios](https://mlsanity.com/paper/2501.16754/) (2025)

## Abstract (arXiv)

We introduce a novel multiframe scene flow approach that jointly optimizes the consistency of the patch appearances and their local rigid motions from RGB-D image sequences. In contrast to the competing methods, we take advantage of an oversegmentation of the reference frame and robust optimization techniques. We formulate scene flow recovery as a global non-linear least squares problem which is iteratively solved by a damped Gauss-Newton approach. As a result, we obtain a qualitatively new level of accuracy in RGB-D based scene flow estimation which can potentially run in real-time. Our method can handle challenging cases with rigid, piecewise rigid, articulated and moderate non-rigid motion, and does not rely on prior knowledge about the types of motions and deformations. Extensive experiments on synthetic and real data show that our method outperforms state-of-the-art.