# SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation

## TL;DR

This paper introduces SceneFlowFields++, a fast, robust, and generic multi-frame scene flow estimation algorithm that combines multi-frame matching, visibility prediction, and interpolation, outperforming existing methods in accuracy and speed.

## Contribution

It presents a novel scene flow algorithm that avoids strong domain assumptions, enabling robust and efficient multi-frame matching with explicit visibility prediction.

## Key findings

- Achieves competitive performance on multiple datasets.
- Runs faster than existing state-of-the-art methods.
- Demonstrates robustness without strong domain assumptions.

## Abstract

State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation. Avoiding strong assumptions on the domain or the problem yields a more robust algorithm. This algorithm is fast because we avoid explicit regularization during matching, which allows an efficient computation. Using image information from multiple time steps and explicit visibility prediction based on previous results, we achieve competitive performances on different data sets. Our contributions and results are evaluated in comparative experiments. Overall, we present an accurate scene flow algorithm that is faster and more generic than any individual benchmark leader.