Related papers: Unsupervised OmniMVS: Efficient Omnidirectional De…
In recent years, unsupervised deep learning approaches have received significant attention to estimate the depth and visual odometry (VO) from unlabelled monocular image sequences. However, their performance is limited in challenging…
With the prosperity of the video surveillance, multiple cameras have been applied to accurately locate pedestrians in a specific area. However, previous methods rely on the human-labeled annotations in every video frame and camera view,…
n this paper, we propose an effective and efficient pyramid multi-view stereo (MVS) net with self-adaptive view aggregation for accurate and complete dense point cloud reconstruction. Different from using mean square variance to generate…
We propose a multi-camera LiDAR-visual-inertial odometry framework, Multi-LVI-SAM, which fuses data from multiple fisheye cameras, LiDAR and inertial sensors for highly accurate and robust state estimation. To enable efficient and…
The advancement of RS technology has enabled high-resolution Earth observation; however, interpreting these images using modern VFMs remains a significant challenge. Unlike object-centric natural images, RS imagery is fundamentally…
Deep learning has shown to be effective for depth inference in multi-view stereo (MVS). However, the scalability and accuracy still remain an open problem in this domain. This can be attributed to the memory-consuming cost volume…
We introduce Point-MVSNet, a novel point-based deep framework for multi-view stereo (MVS). Distinct from existing cost volume approaches, our method directly processes the target scene as point clouds. More specifically, our method predicts…
In this work we present FreDSNet, a deep learning solution which obtains semantic 3D understanding of indoor environments from single panoramas. Omnidirectional images reveal task-specific advantages when addressing scene understanding…
In this study, we present a method for all-around depth estimation from multiple omnidirectional images for indoor environments. In particular, we focus on plane-sweeping stereo as the method for depth estimation from the images. We propose…
Underwater scene reconstruction is essential for immersive exploration of aquatic environments, yet remains challenging due to complex participating-media effects such as absorption and scattering, as well as the limited field of view (FoV)…
In the last decade, numerous supervised deep learning approaches requiring large amounts of labeled data have been proposed for visual-inertial odometry (VIO) and depth map estimation. To overcome the data limitation, self-supervised…
Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal images are independent from environmental illumination, they…
Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving. This study proposes a comprehensive self-supervised framework for accurate scale-aware depth prediction on autonomous…
Estimating the depth of omnidirectional images is more challenging than that of normal field-of-view (NFoV) images because the varying distortion can significantly twist an object's shape. The existing methods suffer from troublesome…
In this work we present a novel multi-view photometric stereo (MVPS) method. Like many works in 3D reconstruction we are leveraging neural shape representations and learnt renderers. However, our work differs from the state-of-the-art…
Surround View fisheye cameras are commonly deployed in automated driving for 360\deg{} near-field sensing around the vehicle. This work presents a multi-task visual perception network on unrectified fisheye images to enable the vehicle to…
State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. They do not generalize well when applied on distance estimation for complex projection models such as in fisheye and…
Multi-view stereo (MVS) is a crucial task for precise 3D reconstruction. Most recent studies tried to improve the performance of matching cost volume in MVS by designing aggregated 3D cost volumes and their regularization. This paper…
Deep learning has recently demonstrated its excellent performance for multi-view stereo (MVS). However, one major limitation of current learned MVS approaches is the scalability: the memory-consuming cost volume regularization makes the…
This study addresses the challenge of online 3D model generation for neural rendering using an RGB image stream. Previous research has tackled this issue by incorporating Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS) as…