Instance Segmentation with Cross-Modal Consistency

TL;DR

This paper presents a novel multi-sensor instance segmentation approach using contrastive learning to produce stable, viewpoint-invariant embeddings across modalities and time, improving scene understanding in robotics.

Contribution

It introduces a contrastive learning framework for multi-modal, multi-temporal instance segmentation that enhances embedding stability and invariance, advancing perception in autonomous systems.

Findings

Embeddings are invariant to viewpoint changes.

Embeddings are consistent across sensor modalities.

Method improves stability of instance masks over time.

Abstract

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple sensor modalities, such as cameras and LiDAR. Our method learns to predict embeddings for each pixel or point that give rise to a dense segmentation of the scene. Specifically, our technique applies contrastive learning to points in the scene both across sensor modalities and the temporal domain. We demonstrate that this formulation encourages the models to learn embeddings that are invariant to viewpoint variations and consistent across sensor modalities. We further demonstrate that the embeddings are stable over time as objects move around the scene. This not only provides stable instance masks, but can also provide valuable signals to downstream tasks, such as object tracking. We evaluate our method on the Cityscapes and KITTI-360 datasets. We further conduct a number of ablation studies, demonstrating benefits when applying additional inputs for the contrastive loss.