Monocular Depth Estimation (MDE) remains a challenging problem due to texture ambiguity, occlusion, and scale variation in real-world scenes. While recent deep learning methods have made significant progress, maintaining structural consistency and ro...
LiDAR sensors provide reliable physical distance measurements using laser signals, enabling accurate acquisition of 3D information for various optical systems. However, they are costly, require significant weight and space, and their reliability and...
In this paper, we propose a novel Depth from Focus (DFF) framework that formulates depth estimation as an energy minimization problem and unrolls the corresponding iterative optimization into a trainable neural architecture. Given a focal stack, a de...
Thermal monocular depth estimation can provide more robust depth predictions than RGB-based methods under nighttime and adverse weather conditions. However, when trained with projected LiDAR supervision, depth models often retain structural errors in...
With the widespread adoption of 3D scanning technology, depth view-driven 3D reconstruction has become crucial for applications such as SLAM, virtual reality, and autonomous vehicles. However, due to the effects of self-occlusion and environmental oc...
As a traditional computer vision task, monocular depth estimation plays an essential role in novel view 3D reconstruction and augmented reality. Convolutional neural network (CNN)-based models have achieved good performance for this task. However, in...
Robotic 3D manipulation of small targets, such as laser ablation of urban-tree fruit balls, requires locally reliable depth. Mainstream RGB-D depth-refinement methods usually optimize image-wide metrics, which can leave task-relevant regions under-re...
Stereo vision measurement in industrial robot environments fails on thin structures such as needles and gripper tips, because both traditional and deep-learning-based stereo matching produce boundary errors there. We identify and verify experimentall...
Deep learning has proved to be a breakthrough in depth generation. However, the generalization ability of deep networks is still limited, and they cannot maintain a satisfactory performance on some inputs. By addressing a similar problem in the segme...
Streaming feed-forward 3D reconstruction produces depth predictions at successive frames, but cross-view geometric consistency and local depth accuracy may vary. We present a training-free, output-level approach that combines Multi-Reference Geometri...
Estimating the 3D shape of a scene from differently focused set of images has been a practical approach for 3D reconstruction with color cameras. However, reconstructed depth with existing depth from focus (DFF) methods still suffer from poor quality...
In this paper, we propose a method to refine the depth maps obtained by Multi-View Stereo (MVS) through iterative optimization of the Neural Radiance Field (NeRF). MVS accurately estimates the depths on object surfaces, and NeRF accurately estimates...
Monocular depth estimation (MDE) is a critical task in computer vision with applications in autonomous driving, robotics, and augmented reality. However, predicting depth from a single image poses significant challenges, especially in dynamic scenes...
Recently, the research on monocular 3D target detection based on pseudo-LiDAR data has made some progress. In contrast to LiDAR-based algorithms, the robustness of pseudo-LiDAR methods is still inferior. After conducting in-depth experiments, we real...
Shape from Focus (SFF) estimates scene depth by analyzing focus variations across a sequence of images captured at different focal settings. Traditional SFF methods rely on handcrafted focus operators that preserve local structural details, but they...
Computer vision tasks, such as motion estimation, depth estimation, object detection, etc., are better suited to light field images with more structural information than traditional 2D monocular images. However, since costly data acquisition instrume...
Underwater visual perception is degraded by wavelength-dependent absorption and scattering, the effects of which vary with the camera-to-scene distance. Many underwater image enhancement methods nevertheless apply image-level transformations or use r...
Adapting monocular metric depth to agricultural imagery requires balancing target-domain accuracy against the scope of model updates and embedded execution cost. We evaluate SARE-Depth on CitrusFarm using a frozen teacher-guided Depth Anything V2 Sma...
We present two algorithms for aligning two colored point clouds. The two algorithms are designed to minimize a probabilistic cost based on the color-supported soft matching of points in a point cloud to their K-closest points in the other point cloud...
While transparent objects present persistent challenges for RGB-D sensing due to complex refraction and reflection effects, these optical phenomena frequently precipitate unreliable depth measurements and compromise depth completion performance. In t...
View synthesis is a crucial technique for free viewpoint video and multi-view video coding because of its capability to render an unlimited number of virtual viewpoints from adjacent captured texture images and corresponding depth maps. The accuracy...
We propose an enhancement module called depth discontinuity learning (DDL) for learning-based multi-view stereo (MVS) methods. Traditional methods are known for their accuracy but struggle with completeness. While recent learning-based methods have i...
The current transmission and reflection laser ablation micropropulsion modes have the problem of a complex working medium supply system in engineering. Therefore, we propose large-spot laser ablation with a one-dimensional supply mode. In order to ve...
The advancement of 3D printing technology has been remarkable, yet the quality of printed prototypes heavily relies on the rheological behavior of the materials used. This study focuses on optimizing geopolymer-based composite formulas to achieve hig...
To take full advantage of the information of images captured by drones and given that most existing monocular depth estimation methods based on supervised learning require vast quantities of corresponding ground truth depth data for training, the mod...
With the majority of research, in relation to 3D object reconstruction, focusing on single static synthetic object reconstruction, there is a need for a method capable of reconstructing morphing objects in dynamic scenes without external influence. H...
The rapid development of autonomous driving has underscored the pivotal role of 3D perception. Monocular 3D object detection, as a cost-effective alternative to expensive lidar systems, is garnering increasing attention. However, existing pseudo-lida...
Depth completion is widely employed in Simultaneous Localization and Mapping (SLAM) and Structure from Motion (SfM), which are of great significance to the development of autonomous driving. Recently, the methods based on the fusion of vision transfo...
Certain obstacle mapping applications require the live evaluation of the measured data to prevent collision with obstacles. The fusion of different or similar sensors usually has a high calculation demand, which increases significantly with the area...
This research endeavors to investigate how the internationalization depth of green innovation enterprises influences their innovation performance and sustainability, specifically analyzing data from China’s Specialized, Fine, Special, and Innov...
Background: Amblyopia is associated with unbalanced suppression between the two eyes. Existing clinical measures of suppression, such as the Worth 4 Dot test, provide qualitative information about suppression but cannot precisely quantify it. The Syn...
Depth completion aims to achieve high-quality dense depth prediction from a pair of synchronized sparse depth map and RGB image, and it plays an important role in many intelligent applications, including urban mapping, scene understanding, autonomous...
This work presents a procedure for refining depth maps acquired using RGB-D (depth) cameras. With numerous new structured-light RGB-D cameras, acquiring high-resolution depth maps has become easy. However, there are problems such as undesired occlus...
The field of hepatocellular carcinoma (HCC) has faced significant change on multiple levels in the past few years. The increasing emphasis on the various HCC phenotypes and the emergence of novel, specific therapies have slowly paved the way for a pe...
We propose a generic depth-refinement scheme based on GeoNet, a recent deep-learning approach for predicting depth and normals from a single color image, and extend it to be applied to any depth reconstruction task such as super resolution, denoising...
Mirror segmentation remains challenging because mirror regions often share appearance with the reflected scene, while sensor depth around mirrors is frequently missing, noisy, or geometrically inconsistent. Although recent RGB-based methods have achi...
A depth estimation algorithm from plenoptic images is presented. There are two stages to estimate the depth. First is the initial estimation base on the epipolar plane images (EPIs). Second is the refinement of the estimations. At the initial estimat...
Refining raw disparity maps from different algorithms to exploit their complementary advantages is still challenging. Uncertainty estimation and complex disparity relationships among pixels limit the accuracy and robustness of existing methods and th...
In this paper, in order to improve the performance of the ZL205A castings, continuous ultrasonic and pulsed ultrasonic treatments were applied to the melted alloy to study the effect of ultrasound propagation distance on microstructure and microhardn...
An artificial compound eye consists of multiple apertures that allow for a large field of view (FOV) while maintaining a small size. Each aperture captures a sub-image, and multiple sub-images are needed to reconstruct the full FOV. The reconstructio...
This paper presents a real-time, robust and low-drift depth-only SLAM (simultaneous localization and mapping) method for depth cameras by utilizing both dense range flow and sparse geometry features from sequential depth images. The proposed method i...
Rare earth elements and transition elements are widely used in aluminum alloys, magnesium alloys and copper alloys due to their unique microalloying effects. With regard to in-depth research on the grain refinement characteristics of rare earth eleme...
In this paper, we propose a novel 2D-to-3D video conversion method for 3D entertainment applications. 3D entertainment is getting more and more popular and can be found in many contexts, such as TV and home gaming equipment. 3D image sensors are a n...
Underwater salient instance segmentation (USIS) remains challenging because color distortion, low contrast, and scattering often weaken appearance cues, while reliable geometric measurements are usually unavailable. Existing methods mainly rely on re...
Object pre-localization from computer-generated holograms is still an open problem in the current state of the art. In this work, we propose the use of the hologram phase space representation to determine a set of regions of interest where the search...
Monocular depth estimation plays a crucial role in applications such as autonomous driving and mobile 3D reconstruction. However, existing lightweight methods are often constrained by limited computational resources and rely on shallow feature repres...
Generalizable 3D Gaussian Splatting enables efficient sparse-view novel view synthesis, but accurate Gaussian center estimation remains challenging. Epipolar attention and cost volume methods exhibit complementary limitations in non-Lambertian region...
T-bar penetrometers are widely utilized for measurements of strength characteristics of soft clay in offshore field investigations and laboratory tests. To obtain strain-softening parameters of marine soft clay, it is necessary to conduct cyclic T-ba...
Over the last few years, deep neural networks have achieved outstanding results in computer vision, and have been widely integrated into mobile robot obstacle avoidance systems, where perception-driven classification supports navigation decisions. Mo...
This paper investigates the combined application of seismic inversion and migration for processing seismic data in the depth domain. Seismic inversion serves as a widely used practical tool allowing the derivation of detailed subsurface models from s...
of 27