… in close-set 3D object detection, existing approaches struggle … a promptable 3D detection
foundation model capable of detecting … Training a foundation model for 3D detection is fun- …

… at constructing arbitrary 3D objects from single-view, in-the-wild images. We commence
by … To surmount these challenges, we devise a versatile framework named Anything3D. …

… 3D detection models struggle with in-the-wild images due to the lack of 3D in-the-wild
datasets and the challenges of 3D … 3D scenes from 2D images to efficiently produce high-quality …

… sees and know where it is in 3D. Today’s vision-… 3D detection remains largely missing from
the VLM toolbox. We present LocateAnything3D, a VLM-native recipe that casts 3D detection …

… We design our 3D object detection framework by extending Faster R-CNN [64] with a … -CNN
by introducing a 3D detection head which predicts a 3D cuboid for each detected 2D object. …

… This paper focuses on the so-called Open World Object Detection problem (OWOD) that
requires detecting previously unseen objects in images and their inclusion in the learning …

… to detect, track, and follow any object in real-time. Our approach, dubbed follow anything (…
(foundation models), FAn can detect and segment objects by matching multimodal queries (…

… embodied 3D perception a promising direction. However, most existing VFM-assisted 3D …
In this paper, we aim to leverage Segment Anything Model (SAM) for real-time 3D instance …

… a new Wild Animal Tracking framework based on the high-quality Segment anything model
(… Therefore, developing a simple and effective re-detection module is beneficial to promote …

… Omni3d: A large benchmark and model for 3d object detection in the wild. In Proceedings
of the IEEE/CVF conference on computer vision and pattern recognition, pages 13154–13164, …