Related papers: Moving Indoor: Unsupervised Video Depth Learning i…
We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences without dense depth…
Monocular depth estimation has been increasingly adopted in robotics and autonomous driving for its ability to infer scene geometry from a single camera. In self-supervised monocular depth estimation frameworks, the network jointly…
Learning to predict scene depth from RGB inputs is a challenging task both for indoor and outdoor robot navigation. In this work we address unsupervised learning of scene depth and robot ego-motion where supervision is provided by monocular…
In this paper, we propose a unified method to jointly learn optical flow and stereo matching. Our first intuition is stereo matching can be modeled as a special case of optical flow, and we can leverage 3D geometry behind stereoscopic…
We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is…
Optical flow estimation is a fundamental problem in computer vision, yet the reliance on expensive ground-truth annotations limits the scalability of supervised approaches. Although unsupervised and semi-supervised methods alleviate this…
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics…
Unsupervised monocular depth estimation has received widespread attention because of its capability to train without ground truth. In real-world scenarios, the images may be blurry or noisy due to the influence of weather conditions and…
Significant attention has been attracted to deep learning-based depth estimates. Dynamic objects become the most hard problems in inter-frame-supervised depth estimates due to the uncertainty in adjacent frames. Thus, integrating optical…
In dense foggy scenes, existing optical flow methods are erroneous. This is due to the degradation caused by dense fog particles that break the optical flow basic assumptions such as brightness and gradient constancy. To address the…
Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…
Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we…
The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods. To further improve the performance, recent works mainly…
Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual…
We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective. Alongside this investigation we construct a…
Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates optical flow and…
Estimating geometric elements such as depth, camera motion, and optical flow from images is an important part of the robot's visual perception. We use a joint self-supervised method to estimate the three geometric elements. Depth network,…
Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are…
The RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will…
Both optical flow and stereo disparities are image matches and can therefore benefit from joint training. Depth and 3D motion provide geometric rather than photometric information and can further improve optical flow. Accordingly, we design…