LabelAny3D: Label Any Object 3D in the Wild
This addresses the lack of 3D in-the-wild datasets for applications like robotics and scene understanding, though it is incremental as it builds on existing methods for annotation.
The paper tackled the problem of detecting objects in 3D space from monocular images in the wild by introducing LabelAny3D, a framework that reconstructs holistic 3D scenes to produce high-quality 3D bounding box annotations, resulting in improved monocular 3D detection performance across benchmarks and outperforming prior auto-labeling approaches.
Detecting objects in 3D space from monocular input is crucial for applications ranging from robotics to scene understanding. Despite advanced performance in the indoor and autonomous driving domains, existing monocular 3D detection models struggle with in-the-wild images due to the lack of 3D in-the-wild datasets and the challenges of 3D annotation. We introduce LabelAny3D, an \emph{analysis-by-synthesis} framework that reconstructs holistic 3D scenes from 2D images to efficiently produce high-quality 3D bounding box annotations. Built on this pipeline, we present COCO3D, a new benchmark for open-vocabulary monocular 3D detection, derived from the MS-COCO dataset and covering a wide range of object categories absent from existing 3D datasets. Experiments show that annotations generated by LabelAny3D improve monocular 3D detection performance across multiple benchmarks, outperforming prior auto-labeling approaches in quality. These results demonstrate the promise of foundation-model-driven annotation for scaling up 3D recognition in realistic, open-world settings.