Related papers: GeoBench: Benchmarking and Analyzing Monocular Geo…

Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and…

We propose a self-supervised learning framework that uses unlabeled monocular video sequences to generate large-scale supervision for training a Visual Odometry (VO) frontend, a network which computes pointwise data associations across…

Monocular depth estimation is the base task in computer vision. It has a tremendous development in the decade with the development of deep learning. But the boundary blur of the depth map is still a serious problem. Research finds the…

Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where…

Generative models are known to be difficult to assess. Recent works, especially on generative adversarial networks (GANs), produce good visual samples of varied categories of images. However, the validation of their quality is still…

Self-supervised monocular depth estimation methods have been increasingly given much attention due to the benefit of not requiring large, labelled datasets. Such self-supervised methods require high-quality salient features and consequently…

Monocular depth estimation is known as an ill-posed task in which objects in a 2D image usually do not contain sufficient information to predict their depth. Thus, it acts differently from other tasks (e.g., classification and segmentation)…

This research paper presents an innovative multi-task learning framework that allows concurrent depth estimation and semantic segmentation using a single camera. The proposed approach is based on a shared encoder-decoder architecture, which…

This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor), which is designed to address the…

A key goal for the advancement of AI is to develop technologies that serve the needs not just of one group but of all communities regardless of their geographical region. In fact, a significant proportion of knowledge is locally shared by…

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We…

Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training. Convolutional neural networks (CNNs) have recently achieved great success in this task. However, their…

Zero-shot depth estimation (DE) models exhibit strong generalization performance as they are trained on large-scale datasets. However, existing models struggle with high-resolution images due to the discrepancy in image resolutions of…

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth…

Generative models can now produce photorealistic imagery, yet they still struggle with the long, multi-goal prompts that professional designers issue. To expose this gap and better evaluate models' performance in real-world settings, we…

Monocular Depth Estimation (MDE) is a fundamental 3D vision problem with numerous applications such as 3D scene reconstruction, autonomous navigation, and AI content creation. However, robust and generalizable MDE remains challenging due to…

We consider the problem of vision-based pose estimation for autonomous systems. While deep neural networks have been successfully used for vision-based tasks, they inherently lack provable guarantees on the correctness of their output,…

Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a growing concern for fairness and information integrity. Research on generative engine…

Unsupervised machine learning lacks ground truth by definition. This poses a major difficulty when designing metrics to evaluate the performance of such algorithms. In sharp contrast with supervised learning, for which plenty of quality…

Different environments pose a great challenge to the outdoor robust visual perception for long-term autonomous driving, and the generalization of learning-based algorithms on different environments is still an open problem. Although…