3260 papers • 126 benchmarks • 313 datasets
Object detection in indoor scenes is the task of performing object detection within an indoor environment. ( Image credit: Faster Bounding Box Annotation for Object Detection in Indoor Scenes )
(Image credit: Papersgraph)
These leaderboards are used to track progress in object-detection-in-indoor-scenes
Use these libraries to find object-detection-in-indoor-scenes models and implementations
No subtasks available.
This work directly operates on raw point clouds by popping up RGBD scans and leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects.
The approach simCrossTrans is named: simple cross-modality transfer learning with ConvNets or ViTs, which surpasses the previous state-of-the-art (SOTA) by a large margin and is easy to implement and expand.
A new geocentric embedding is proposed for depth images that encodes height above ground and angle with gravity for each pixel in addition to the horizontal disparity to facilitate the use of perception in fields like robotics.
It is pointed out that by using a vision transformer together with cross/inter modality transfer learning, a unified detector can achieve better performances when using different modalities as inputs.
Adding a benchmark result helps the community track progress.