StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation
This dataset addresses the need for large-scale, annotated data for 6D pose estimation, particularly for objects with challenging properties like transparency, which is important for researchers in computer vision and robotics, though it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of 6D object pose estimation by introducing a large-scale stereo image dataset called StereOBJ-1M, which includes over 393K frames and 1.5M annotations of 18 objects to address challenges like transparency and specular reflection, and they benchmarked state-of-the-art methods while proposing a novel pose optimization technique.
We present a large-scale stereo RGB image object pose estimation dataset named the $\textbf{StereOBJ-1M}$ dataset. The dataset is designed to address challenging cases such as object transparency, translucency, and specular reflection, in addition to the common challenges of occlusion, symmetry, and variations in illumination and environments. In order to collect data of sufficient scale for modern deep learning models, we propose a novel method for efficiently annotating pose data in a multi-view fashion that allows data capturing in complex and flexible environments. Fully annotated with 6D object poses, our dataset contains over 393K frames and over 1.5M annotations of 18 objects recorded in 182 scenes constructed in 11 different environments. The 18 objects include 8 symmetric objects, 7 transparent objects, and 8 reflective objects. We benchmark two state-of-the-art pose estimation frameworks on StereOBJ-1M as baselines for future work. We also propose a novel object-level pose optimization method for computing 6D pose from keypoint predictions in multiple images. Project website: https://sites.google.com/view/stereobj-1m.