Constructing Category-Specific Models for Monocular Object-SLAM

TL;DR

This paper introduces a real-time monocular object-SLAM system that constructs category-level models from CAD data, enabling object shape estimation and improved robustness over traditional feature-based SLAM.

Contribution

It develops a novel rendering pipeline for data synthesis, learns category models for 3D deformations and 2D features, and integrates these into a monocular SLAM framework for improved object and scene understanding.

Findings

First instance-independent monocular object-SLAM system.

Enhanced robustness in feature-sparse scenarios.

Successful evaluation on real-world challenging scenes.

Abstract

We present a new paradigm for real-time object-oriented SLAM with a monocular camera. Contrary to previous approaches, that rely on object-level models, we construct category-level models from CAD collections which are now widely available. To alleviate the need for huge amounts of labeled data, we develop a rendering pipeline that enables synthesis of large datasets from a limited amount of manually labeled data. Using data thus synthesized, we learn category-level models for object deformations in 3D, as well as discriminative object features in 2D. These category models are instance-independent and aid in the design of object landmark observations that can be incorporated into a generic monocular SLAM framework. Where typical object-SLAM approaches usually solve only for object and camera poses, we also estimate object shape on-the-fly, allowing for a wide range of objects from the category to be present in the scene. Moreover, since our 2D object features are learned discriminatively, the proposed object-SLAM system succeeds in several scenarios where sparse feature-based monocular SLAM fails due to insufficient features or parallax. Also, the proposed category-models help in object instance retrieval, useful for Augmented Reality (AR) applications. We evaluate the proposed framework on multiple challenging real-world scenes and show --- to the best of our knowledge --- first results of an instance-independent monocular object-SLAM system and the benefits it enjoys over feature-based SLAM methods.