aiqbench analysis
PIXIE advances industrial robotics by enabling zero-shot 6D pose estimation using only untextured geometric models, effectively bypassing the need for resource-heavy data pipelines or reliance on surface textures. This approach significantly improves robustness against real-world variables such as lighting changes, assembly defects, and occlusions without requiring object-specific training. The introduction of a novel dataset featuring these specific imperfections provides a crucial benchmark for future research in resilient computer vision systems.
PIXIE: A Zero-Shot texture-invariant 6D pose estimation framework for unseen objects with assembly defects
arXiv:2607.16015v1 Announce Type: cross Abstract: 6D pose estimation remains a key challenge in robotics and computer vision, particularly in industrial environments. The deployment of currently available data-driven methods is often limited by resource-intensive data pipelines, reliance on textured 3D models, and sensitivity to geometric deviations caused by damages or assembly defects. We present PIXIE, a zero-shot framework that estimates the 6D pose of an object from an RGB image using only an untextured 3D model. Synthetic depth and normal maps are rendered from sampled reference viewpoints and matched to the query image via a pretrained cross-modality feature matcher. Matched keypoints are back-projected to obtain 2D--3D correspondences for PnP-based pose estimation. Relying exclusively on geometry makes the method inherently robust to lighting and texture variation, while correspondence filtering handles geometric deviations between the model and physical object. We evaluate on widely-used public benchmarks, reporting state-of-the-art results on texture-less objects without object-specific training, and introduce a novel dataset with assembly defects, texture variations, and occlusion to demonstrate real-world applicability.
Abstract:6D pose estimation remains a key challenge in robotics and computer vision, particularly in industrial environments. The deployment of currently available data-driven methods is often limited by resource-intensive data pipelines, reliance on textured 3D models, and sensitivity to geometric deviations caused by damages or assembly defects. We present PIXIE, a zero-shot framework that estimates the 6D pose of an object from an RGB image using only an untextured 3D model. Synthetic depth and normal maps are rendered from sampled reference viewpoints and matched to the query image via a pretrained cross-modality feature matcher. Matched keypoints are back-projected to obtain 2D--3D correspondences for PnP-based pose estimation. Relying exclusively on geometry makes the method inherently robust to lighting and texture variation, while correspondence filtering handles geometric deviations between the model and physical object. We evaluate on widely-used public benchmarks, reporting state-of-the-art results on texture-less objects without object-specific training, and introduce a novel dataset with assembly defects, texture variations, and occlusion to demonstrate real-world applicability.
This work has been accepted for publication in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026. The final published version will be available via IEEE Xplore
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2607.16015 [cs.CV]
(or arXiv:2607.16015v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.16015 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 213 words
Related coverage
PIXIE: A Zero-Shot texture-invariant 6D pose estimation framework for unseen objects with assembly defects
arXiv · Jul 21, 2026
Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives
arXiv · Jun 4, 2026
AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulation
arXiv · Sep 5, 2026
WAPR: A Foundation Model for Wide-Angle Refinement in Unseen Object Pose Estimation
arXiv · Oct 8, 2026