4 papers
DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval
Xinwei He, Yansong Zheng, Qianru Han +7
Vision foundation models have shown great promise for open-set 3D object retrieval (3DOR) through efficient adaptation to multi-view images. Leveraging semantically aligned latent…
Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval
Zhichuan Wang, Yang Zhou, Zhe Liu +5
Open-set 3D object retrieval (3DOR) is an emerging task aiming to retrieve 3D objects of unseen categories beyond the training set. Existing methods typically utilize all modalitie…
TeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment
Zhichuan Wang, Yang Zhou, Jinhai Xiang +2
Learning discriminative 3D representations that generalize well to unknown testing categories is an emerging requirement for many real-world 3D applications. Existing well-establis…
Omni-AD: Learning to Reconstruct Global and Local Features for Multi-class Anomaly Detection
Jiajie Quan, Ao Tong, Yuxuan Cai +3
In multi-class unsupervised anomaly detection(MUAD), reconstruction-based methods learn to map input images to normal patterns to identify anomalous pixels. However, this strategy…