NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation

TL;DR

NeRF-Pose introduces a weakly-supervised pipeline for 6D object pose estimation that reconstructs objects with neural representations and regresses poses from minimal annotations, achieving state-of-the-art accuracy.

Contribution

It proposes a novel first-reconstruct-then-regress approach using neural implicit representations trained with weak labels for 6D pose estimation.

Findings

Achieves state-of-the-art accuracy on LineMod datasets.

Requires only 2D segmentation and relative camera poses for training.

Operates with a single image at inference.

Abstract

Pose estimation of 3D objects in monocular images is a fundamental and long-standing problem in computer vision. Existing deep learning approaches for 6D pose estimation typically rely on the assumption of availability of 3D object models and 6D pose annotations. However, precise annotation of 6D poses in real data is intricate, time-consuming and not scalable, while synthetic data scales well but lacks realism. To avoid these problems, we present a weakly-supervised reconstruction-based pipeline, named NeRF-Pose, which needs only 2D object segmentation and known relative camera poses during training. Following the first-reconstruct-then-regress idea, we first reconstruct the objects from multiple views in the form of an implicit neural representation. Then, we train a pose regression network to predict pixel-wise 2D-3D correspondences between images and the reconstructed model. At inference, the approach only needs a single image as input. A NeRF-enabled PnP+RANSAC algorithm is used to estimate stable and accurate pose from the predicted correspondences. Experiments on LineMod and LineMod-Occlusion show that the proposed method has state-of-the-art accuracy in comparison to the best 6D pose estimation methods in spite of being trained only with weak labels. Besides, we extend the Homebrewed DB dataset with more real training images to support the weakly supervised task and achieve compelling results on this dataset. The extended dataset and code will be released soon.