Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimation

TL;DR

This paper introduces a novel Deep Fusion Transformer block for better cross-modality feature integration in 6D object pose estimation from RGBD images, along with a weighted voting algorithm for precise keypoint localization, achieving state-of-the-art results.

Contribution

The paper proposes a new Deep Fusion Transformer for improved cross-modality feature fusion and a weighted voting algorithm for robust, real-time 3D keypoint localization in pose estimation.

Findings

Outperforms existing methods on four benchmarks.

Demonstrates strong generalization capability.

Achieves near real-time inference.

Abstract

One critical challenge in 6D object pose estimation from a single RGBD image is efficient integration of two different modalities, i.e., color and depth. In this work, we tackle this problem by a novel Deep Fusion Transformer~(DFTr) block that can aggregate cross-modality features for improving pose estimation. Unlike existing fusion methods, the proposed DFTr can better model cross-modality semantic correlation by leveraging their semantic similarity, such that globally enhanced features from different modalities can be better integrated for improved information extraction. Moreover, to further improve robustness and efficiency, we introduce a novel weighted vector-wise voting algorithm that employs a non-iterative global optimization strategy for precise 3D keypoint localization while achieving near real-time inference. Extensive experiments show the effectiveness and strong generalization capability of our proposed 3D keypoint voting algorithm. Results on four widely used benchmarks also demonstrate that our method outperforms the state-of-the-art methods by large margins.