Related papers: ProDepth: Boosting Self-Supervised Multi-Frame Mon…
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over…
Monocular depth estimation (MDE) aims to infer per-pixel depth from a single RGB image. While diffusion models have advanced MDE with impressive generalization, they often exhibit limitations in accurately reconstructing far-range regions.…
Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity of annotations makes the task challenging. Supervised models produce concave objects due to insufficient structural information. They overfit to valid…
This work introduces an effective and practical solution to the dense two-view structure from motion (SfM) problem. One vital question addressed is how to mindfully use per-pixel optical flow correspondence between two frames for accurate…
Self-supervised monocular depth estimation enables robots to learn 3D perception from raw video streams. This scalable approach leverages projective geometry and ego-motion to learn via view synthesis, assuming the world is mostly static.…
In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance. However, reconstructing smooth and detailed surfaces in…
In this paper, we propose a dense monocular SLAM system, named DeepRelativeFusion, that is capable to recover a globally consistent 3D structure. To this end, we use a visual SLAM algorithm to reliably recover the camera poses and…
Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years. Although current methods have reached a high up-to-scale accuracy, they usually fail to learn the true scale metric due to the…
Self-supervised monocular depth estimation serves as a key task in the development of endoscopic navigation systems. However, performance degradation persists due to uneven illumination inherent in endoscopic images, particularly in…
Depth estimation is a core problem in robotic perception and vision tasks, but 3D reconstruction from a single image presents inherent uncertainties. Current depth estimation models primarily rely on inter-image relationships for supervised…
We propose a learning-based method that solves monocular stereo and can be extended to fuse depth information from multiple target frames. Given two unconstrained images from a monocular camera with known intrinsic calibration, our network…
In the last year, universal monocular metric depth estimation (universal MMDE) has gained considerable attention, serving as the foundation model for various multimedia tasks, such as video and image editing. Nonetheless, current approaches…
Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity assumption. When observing a dynamic environment, this…
Recent geometric methods need reliable estimates of 3D motion parameters to procure accurate dense depth map of a complex dynamic scene from monocular images \cite{kumar2017monocular, ranftl2016dense}. Generally, to estimate…
Depth estimation is critical for any robotic system. In the past years estimation of depth from monocular images have shown great improvement, however, in the underwater environment results are still lagging behind due to appearance changes…
An event camera is a novel vision sensor that can capture per-pixel brightness changes and output a stream of asynchronous ``events''. It has advantages over conventional cameras in those scenes with high-speed motions and challenging…
A well-known challenge in applying deep-learning methods to omnidirectional images is spherical distortion. In dense regression tasks such as depth estimation, where structural details are required, using a vanilla CNN layer on the…
Existing 3D scene flow estimation methods provide the 3D geometry and 3D motion of a scene and gain a lot of interest, for example in the context of autonomous driving. These methods are traditionally based on a temporal series of stereo…
Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and…
We present a novel method to train machine learning algorithms to estimate scene depths from a single image, by using the information provided by a camera's aperture as supervision. Prior works use a depth sensor's outputs or images of the…