MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular Images

TL;DR

MonoPLFlowNet is a novel deep learning architecture that estimates real-scale 3D scene flow and depth from only two monocular images, outperforming existing monocular methods and rivaling LiDAR-based approaches.

Contribution

This work introduces MonoPLFlowNet, the first monocular image-based method to accurately estimate real-scale 3D scene flow and depth without additional ground truth data.

Findings

Outperforms state-of-the-art monocular scene flow methods in real scale

Achieves comparable accuracy to LiDAR-based approaches

Provides more accurate depth estimation than existing monocular methods

Abstract

Real-scale scene flow estimation has become increasingly important for 3D computer vision. Some works successfully estimate real-scale 3D scene flow with LiDAR. However, these ubiquitous and expensive sensors are still unlikely to be equipped widely for real application. Other works use monocular images to estimate scene flow, but their scene flow estimations are normalized with scale ambiguity, where additional depth or point cloud ground truth are required to recover the real scale. Even though they perform well in 2D, these works do not provide accurate and reliable 3D estimates. We present a deep learning architecture on permutohedral lattice - MonoPLFlowNet. Different from all previous works, our MonoPLFlowNet is the first work where only two consecutive monocular images are used as input, while both depth and 3D scene flow are estimated in real scale. Our real-scale scene flow estimation outperforms all state-of-the-art monocular-image based works recovered to real scale by ground truth, and is comparable to LiDAR approaches. As a by-product, our real-scale depth estimation also outperforms other state-of-the-art works.