Related papers: Scale-invariant and View-relational Representation…

Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data…

Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific…

Estimating depth from a single image is a challenging visual task. Compared to relative depth estimation, metric depth estimation attracts more attention due to its practical physical significance and critical applications in real-life…

Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods…

Learning based on multimodal data has attracted increasing interest recently. While a variety of sensory modalities can be collected for training, not all of them are always available in development scenarios, which raises the challenge to…

Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT)…

Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervised knowledge distillation (SSKD) framework that compresses…

Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with…

We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised manner. By exploiting the geometric…

We propose SharpDepth, a novel approach to monocular metric depth estimation that combines the metric accuracy of discriminative depth estimation methods (e.g., Metric3D, UniDepth) with the fine-grained boundary sharpness typically achieved…

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…

Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial…

Accurate monocular depth estimation remains a challenging problem due to the inherent ambiguity that stems from the ill-posed nature of recovering 3D structure from a single view, where multiple plausible depth configurations can produce…

Monocular depth estimation is a crucial task to measure distance relative to a camera, which is important for applications, such as robot navigation and self-driving. Traditional frame-based methods suffer from performance drops due to the…

Estimating precise metric depth and scene reconstruction from monocular endoscopy is a fundamental task for surgical navigation in robotic surgery. However, traditional stereo matching adopts binocular images to perceive the depth…

Recently, radar-camera fusion algorithms have gained significant attention as radar sensors provide geometric information that complements the limitations of cameras. However, most existing radar-camera depth estimation algorithms focus…

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we…

Spatial scene understanding, including monocular depth estimation, is an important problem in various applications, such as robotics and autonomous driving. While improvements in unsupervised monocular depth estimation have potentially…

Monocular 3D object detection is a low-cost but challenging task, as it requires generating accurate 3D localization solely from a single image input. Recent developed depth-assisted methods show promising results by using explicit depth…

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…