|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Learning based methods have shown very promising results for the task of depth estimation in single images.
#7 best model for Monocular Depth Estimation on KITTI Eigen split
Despite the progress on monocular depth estimation in recent years, we show that the gap between monocular and stereo depth accuracy remains large$-$a particularly relevant result due to the prevalent reliance upon monocular cameras by vehicles that are expected to be self-driving.
Per-pixel ground-truth depth data is challenging to acquire at scale.
#5 best model for Monocular Depth Estimation on KITTI Eigen split
Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction.
Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner.
Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera.
We propose a novel appearance-based Object Detection system that is able to detect obstacles at very long range and at a very high speed (~300Hz), without making assumptions on the type of motion.
These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions.
Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.
#4 best model for Monocular Depth Estimation on NYU-Depth V2
Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks.