Context Enhanced Transformer for Single Image Object Detection.

Seungjun An Seonghoon Park Gyeongnyeon Kim Jeongyeol Baek Byeongwon Lee Seungryong Kim

Published in: CoRR (2023)

Keyphrases

single image
object detection
multiple images
shape recovery
d scene
image pairs
indoor scenes
super resolution
light source
shape from shading
scene understanding
partially occluded
intrinsic images
spherical harmonics
vanishing points
human detection
denoising
motion estimation
d objects
computer vision