Related papers: PacGDC: Label-Efficient Generalizable Depth Comple…

Depth completion aims to recover a dense depth map from the sparse depth data and the corresponding single RGB image. The observed pixels provide the significant guidance for the recovery of the unobserved pixels' depth. However, due to the…

Depth maps are widely used in feed-forward 3D Gaussian Splatting (3DGS) pipelines by unprojecting them into 3D point clouds for novel view synthesis. This approach offers advantages such as efficient training, the use of known camera poses,…

This paper investigates the effective utilization of unlabeled data for large-area cross-view geo-localization (CVGL), encompassing both unsupervised and semi-supervised settings. Common approaches to CVGL rely on ground-satellite image…

Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving. Although several works are proposed to jointly train these two tasks using some small…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Depth estimation is one of the essential tasks to be addressed when creating mobile autonomous systems. While monocular depth estimation methods have improved in recent times, depth completion provides more accurate and reliable depth maps…

Depth map enhancement using paired high-resolution RGB images offers a cost-effective solution for improving low-resolution depth data from lightweight ToF sensors. Nevertheless, naively adopting a depth estimation pipeline to fuse the two…

Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open in this field: dealing with non-Lambertian materials and…

Transparent and specular objects are frequently encountered in daily life, factories, and laboratories. However, due to the unique optical properties, the depth information on these objects is usually incomplete and inaccurate, which poses…

We describe a method for unpaired realistic depth synthesis that learns diverse variations from the real-world depth scans and ensures geometric consistency between the synthetic and synthesized depth. The synthesized realistic depth can…

Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge to the model's representation, limiting its ability to…

Accurate surround-view depth estimation provides a competitive alternative to laser-based sensors and is essential for 3D scene understanding in autonomous driving. While empirical studies have proposed various approaches that primarily…

Considerable progress has been made in domain generalization (DG) which aims to learn a generalizable model from multiple well-annotated source domains to unknown target domains. However, it can be prohibitively expensive to obtain…

Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…

Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. Conventional methods focused on extracting a pseudo label…

Data augmentation is crucial for improving the robustness of face detection systems, especially under challenging conditions such as occlusion, illumination variation, and complex environments. Traditional copy paste augmentation often…

Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages…

Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques…

Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and their surroundings, as well as the reliance on noisy pseudo-labels that hinder fine-grained texture…

Robots are often required to localize in environments with unknown object classes and semantic ambiguity. However, when performing global localization using semantic objects, high semantic ambiguity intensifies object misclassification and…