Search Results for author:
Found 5 papers, 3 papers with code
Depth-based 6DoF Object Pose Estimation using Swin Transformer
To tackle this challenge, we propose a novel framework called SwinDePose, that uses only geometric information from depth images to achieve accurate 6D pose estimation.
Unified Object Detector for Different Modalities based on Vision Transformers
We evaluate our unified model on the SUN RGB-D dataset, and demonstrate that it achieves similar or better performance in terms of mAP50 compared to state-of-the-art methods in the SUNRGBD16 category, and comparable performance in point cloud only mode.
Ranked #1 on
Object Detection In Indoor Scenes
on SUN RGB-D
simCrossTrans: A Simple Cross-Modality Transfer Learning for Object Detection with ConvNets or Vision Transformers
Most transfer learning systems are based on the same modality (e. g. RGB image in CV and text in NLP).
Ranked #3 on
Object Detection In Indoor Scenes
on SUN RGB-D
3D Object Detection and Instance Segmentation from 3D Range and 2D Color Images
Instance segmentation and object detection are significant problems in the fields of computer vision and robotics.
Ranked #7 on
3D Object Detection
on SUN-RGBD
Frustum VoxNet for 3D object detection from RGB-D or Depth images
Recently, there have been a plethora of classification and detection systems from RGB as well as 3D images.
Ranked #1 on
3D Object Detection
on SUN-RGBD val
(Inference Speed (s) metric)
