Search papers, labs, and topics across Lattice.
Zhejiang University
4
3
5
A single feed-forward transformer now achieves state-of-the-art performance across diverse video geometry estimation tasks, rivaling specialized architectures.
Forget complex architectures: a simple transformer can generate metric-accurate dense depth maps from sparse observations, outperforming existing methods.
By injecting 2D instance cues from camera data into the BEV space of 4D radar data, SIFormer overcomes radar's sparse geometry and significantly boosts 3D object detection accuracy.
Overcome the extreme sparsity and noise of 4D radar data with SD4R, a new method that significantly boosts 3D object detection performance.
