Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints

TL;DR

This paper introduces certifiably optimal and outlier-robust methods for category-level 3D object pose and shape estimation from 2D/3D keypoints, advancing robustness and accuracy in perception tasks.

Contribution

It develops the first certifiably optimal solvers for pose and shape estimation using semidefinite relaxations, and proposes a graph-theoretic framework for outlier pruning in category-level perception.

Findings

PACE3D* and PACE2D* are the first certifiably optimal solvers for pose and shape estimation.

The proposed ROBIN framework effectively filters out outliers using hypergraph maximum hyperclique computation.

PACE3D# outperforms state-of-the-art vehicle pose estimation methods on ApolloScape datasets.

Abstract

We consider a category-level perception problem, where one is given 2D or 3D sensor data picturing an object of a given category (e.g., a car), and has to reconstruct the 3D pose and shape of the object despite intra-class variability (i.e., different car models have different shapes). We consider an active shape model, where -- for an object category -- we are given a library of potential CAD models describing objects in that category, and we adopt a standard formulation where pose and shape are estimated from 2D or 3D keypoints via non-convex optimization. Our first contribution is to develop PACE3D* and PACE2D*, the first certifiably optimal solvers for pose and shape estimation using 3D and 2D keypoints, respectively. Both solvers rely on the design of tight (i.e., exact) semidefinite relaxations. Our second contribution is to develop outlier-robust versions of both solvers, named PACE3D# and PACE2D#. Towards this goal, we propose ROBIN, a general graph-theoretic framework to prune outliers, which uses compatibility hypergraphs to model measurements' compatibility. We show that in category-level perception problems these hypergraphs can be built from the winding orders of the keypoints (in 2D) or their convex hulls (in 3D), and many outliers can be filtered out via maximum hyperclique computation. The last contribution is an extensive experimental evaluation. Besides providing an ablation study on simulated datasets and on the PASCAL3D+ dataset, we combine our solver with a deep keypoint detector, and show that PACE3D# improves over the state of the art in vehicle pose estimation in the ApolloScape datasets, and its runtime is compatible with practical applications. We release our code at https://github.com/MIT-SPARK/PACE.