Related papers: MP-SfM: Monocular Surface Priors for Robust Struct…
Structure from Motion (SfM) techniques are being increasingly used to create 3D maps from images in many domains including environmental monitoring. However, SfM techniques are often confounded in visually repetitive environments as they…
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal…
Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to predict accurate pixel-wise depth without using labeled…
Semi-Global Matching (SGM) is a widely-used efficient stereo matching technique. It works well for textured scenes, but fails on untextured slanted surfaces due to its fronto-parallel smoothness assumption. To remedy this problem, we…
Unsupervised monocular depth learning generally relies on the photometric relation among temporally adjacent images. Most of previous works use both mean absolute error (MAE) and structure similarity index measure (SSIM) with conventional…
In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF). Unlike existing neural network based…
Self-supervised monocular scene flow estimation, aiming to understand both 3D structures and 3D motions from two temporally consecutive monocular images, has received increasing attention for its simple and economical sensor setup. However,…
Monocular depth estimation is a crucial task in computer vision. While existing methods have shown impressive results under standard conditions, they often face challenges in reliably performing in scenarios such as low-light or rainy…
Structure from motion (SfM) has recently been formulated as a self-supervised learning problem, where neural network models of depth and egomotion are learned jointly through view synthesis. Herein, we address the open problem of how to…
Medical image segmentation is a fundamental task for medical image analysis and surgical planning. In recent years, UNet-based networks have prevailed in the field of medical image segmentation. However, convolution-neural networks (CNNs)…
Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applicability of SLAM…
Current non-rigid structure from motion (NRSfM) algorithms are mainly limited with respect to: (i) the number of images, and (ii) the type of shape variability they can handle. This has hampered the practical utility of NRSfM for many…
Creating 3D models through the Structure from Motion technique is a recognized, efficient, cost-effective structural monitoring strategy. This technique is applied in several engineering fields, particularly for creating models of large…
Accurately reconstructing dense and semantically annotated 3D meshes from monocular images remains a challenging task due to the lack of geometry guidance and imperfect view-dependent 2D priors. Though we have witnessed recent advancements…
In this paper a low-drift monocular SLAM method is proposed targeting indoor scenarios, where monocular SLAM often fails due to the lack of textured surfaces. Our approach decouples rotation and translation estimation of the tracking…
While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in image and video understanding, their ability to comprehend the physical world has become an increasingly important research focus. Despite their…
Self-supervised monocular depth estimation has achieved impressive performance on outdoor datasets. Its performance however degrades notably in indoor environments because of the lack of textures. Without rich textures, the photometric…
Light-weight time-of-flight (ToF) depth sensors are compact and cost-efficient, and thus widely used on mobile devices for tasks such as autofocus and obstacle detection. However, due to the sparse and noisy depth measurements, these…
Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous events instead of intensity frames. Compared to conventional image sensors, they offer significant advantages: high temporal resolution,…
This paper proposes a self-supervised monocular image-to-depth prediction framework that is trained with an end-to-end photometric loss that handles not only 6-DOF camera motion but also 6-DOF moving object instances. Self-supervision is…