Sparse Multiview Open-Vocabulary 3D Detection
This addresses the problem of limited category detection in 3D vision for robotics and vision systems by enabling training-free, open-vocabulary detection, though it is incremental as it builds on existing 2D models.
The paper tackles open-vocabulary 3D object detection in sparse-view settings using only a few posed RGB images, achieving competitive performance with state-of-the-art methods in dense scenarios and significantly outperforming them in sparse-view cases.
The ability to interpret and comprehend a 3D scene is essential for many vision and robotics systems. In numerous applications, this involves 3D object detection, i.e.~identifying the location and dimensions of objects belonging to a specific category, typically represented as bounding boxes. This has traditionally been solved by training to detect a fixed set of categories, which limits its use. In this work, we investigate open-vocabulary 3D object detection in the challenging yet practical sparse-view setting, where only a limited number of posed RGB images are available as input. Our approach is training-free, relying on pre-trained, off-the-shelf 2D foundation models instead of employing computationally expensive 3D feature fusion or requiring 3D-specific learning. By lifting 2D detections and directly optimizing 3D proposals for featuremetric consistency across views, we fully leverage the extensive training data available in 2D compared to 3D. Through standard benchmarks, we demonstrate that this simple pipeline establishes a powerful baseline, performing competitively with state-of-the-art techniques in densely sampled scenarios while significantly outperforming them in the sparse-view setting.