2 papers
cs.CV2025
StereoDETR: Stereo-based Transformer for 3D Object Detection
Shiyi Mu, Zichong Gu, Zhiqi Ai +3
Compared to monocular 3D object detection, stereo-based 3D methods offer significantly higher accuracy but still suffer from high computational overhead and latency. The state-of-t…
eess.IV2024
A Learnable Color Correction Matrix for RAW Reconstruction
Anqi Liu, Shiyi Mu, Shugong Xu
Autonomous driving algorithms usually employ sRGB images as model input due to their compatibility with the human visual system. However, visually pleasing sRGB images are possibly…