Learning Independent Object Motion from Unlabelled Stereoscopic Videos

Abstract

We present a system for learning motion of independently moving objects from stereo videos. The only human annotation used in our system are 2D object bounding boxes which introduce the notion of objects to our system. Unlike prior learning based work which has focused on predicting dense pixel-wise optical flow field and/or a depth map for each image, we propose to predict object instance specific 3D scene flow maps and instance masks from which we are able to derive the motion direction and speed for each object instance. Our network takes the 3D geometry of the problem into account which allows it to correlate the input images. We present experiments evaluating the accuracy of our 3D flow vectors, as well as depth maps and projected 2D optical flow where our jointly learned system outperforms earlier approaches trained for each task independently.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• SfM-Net: Learning of Structure and Motion from Video
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• End-to-End Learning of Geometry and Context for Deep Stereo Regression
• Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding

Cited by in corpus (3)

• RAFT-3D: Scene Flow using Rigid-Motion Embeddings
• RANSAC-Flow: generic two-stage image alignment
• Instance-wise Depth and Motion Learning from Monocular Videos