High-quality 3D ground-truth shapes are critical for 3D object reconstru...
Training a Neural Radiance Field (NeRF) without pre-computed camera pose...
Ensemble learning serves as a straightforward way to improve the perform...
Self-supervised monocular depth estimation has shown impressive results ...
We propose a monocular depth estimator SC-Depth, which requires only
unl...
Multi-view geometry-based methods dominate the last few decades in monoc...
The high computational cost of neural networks has prevented recent succ...
Person search aims to localize and identify a specific person from a gal...
Single-view depth estimation using CNNs trained from unlabelled videos h...
Is recurrent network really necessary for learning a good visual
represe...
Triplet loss has been widely employed in a wide range of computer vision...
Recent work has shown that CNN-based depth and ego-motion estimators can...
Matching two images while estimating their relative geometry is a key st...
Nonlinear regression has been extensively employed in many computer visi...