To improve the DOA estimation, a novel atomic norm-based method is proposed to remove the interference signals by the sparse reconstruction.
In this paper, we introduce a simple framework for Monocular DEtection with depth-aware TRansformer, named MonoDETR.
On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D.
We reverse the conventional design of applying convolution on voxels and attention to points.
Ranked #12 on 3D Part Segmentation on ShapeNet-Part
This paper proposes a landmark detection network for detecting sutures in endoscopic pictures, which solves the problem of a variable number of suture points in the images.