Secondly, we conduct an exhaustive validation process of monocular and stereo depth estimation algorithms designed on visible spectrum bands to benchmark their performance in the thermal image domain.
Therefore, there has been a demand for a lightweight alpha matting model due to the limited computational resources of commercial portable devices.
In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation.
In this paper, we present MC-Calib, a novel and robust toolbox dedicated to the calibration of complex synchronized multi-camera systems using an arbitrary number of fiducial marker-based patterns.
The proposed SALT consists of two blocks: Transformers and linear layers blocks that take advantage of shared attention matrices.
In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion.
Ranked #1 on Depth Completion on NYU-Depth V2
In this paper, we propose a noise-aware exposure control algorithm for robust robot vision.
Keypoint detection usually results in a large number of keypoints which are mostly clustered, redundant, and noisy.
Our method implicitly learns an attention map, which leads to a content-aware shift map for image retargeting.
In this paper, we introduce robust and synergetic hand-crafted features and a simple but efficient deep feature from a convolutional neural network (CNN) architecture for defocus estimation.
Ranked #2 on Defocus Estimation on CUHK - Blur Detection Dataset
This paper introduces an algorithm that accurately estimates depth maps using a lenslet light field camera.