Fusing Local Similarities For Retrieval-based 3D Orientation Estimation Of Unseen Objects

Abstract

In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images. This task contrasts with the one considered by most existing deep learning methods which typically assume that the testing objects have been observed during training. To handle the unseen objects, we follow a retrieval-based strategy and prevent the network from learning object-specific features by computing multi-scale local similarities between the query image and synthetically-generated reference images. We then introduce an adaptive fusion module that robustly aggregates the local similarities into a global similarity score of pairwise images. Furthermore, we speed up the retrieval process by developing a fast retrieval strategy. Our experiments on the LineMOD, LineMOD-Occluded, and T-LESS datasets show that our method yields a significantly better generalization to unseen objects than previous works. Our code and pre-trained models are available at https://sailor-

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keyzhao2022fusing

Related papers

• Latformer: Locality-aware Point-view Fusion Transformer For 3D Shape Recognition (2021)6.34
• Localizing And Orienting Street Views Using Overhead Imagery (2016)17.26
• Location Field Descriptors: Single Image 3D Model Retrieval In The Wild (2019)11.39
• Multiview Image-based Localization (2025)0.00
• Generalizing Single-view 3D Shape Retrieval To Occlusions And Unseen Objects (2023)5.24
• DH3D: Deep Hierarchical 3D Descriptors For Robust Large-scale 6dof Relocalization (2020)14.76
• Visible Structure Retrieval For Lightweight Image-based Relocalisation (2025)0.00
• DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features (2021)15.95