Search Results for author:
Found 3 papers, 3 papers with code
PanopticNDT: Efficient and Robust Panoptic Mapping
As the application scenarios of mobile robots are getting more complex and challenging, scene understanding becomes increasingly crucial.
Ranked #1 on
3D Semantic Segmentation
on Hypersim
Efficient Multi-Task Scene Analysis with RGB-D Transformers
However, we show that the dual CNN-based encoder of EMSANet can be replaced with a single Transformer-based encoder.
Ranked #5 on
Semantic Segmentation
on ScanNetV2
Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments
In order to evaluate our multi-task approach, we extend the annotations of the common RGB-D indoor datasets NYUv2 and SUNRGB-D for instance segmentation and orientation estimation.
