Related papers: Localization-Guided Foreground Augmentation in Aut…
An accurate understanding of a self-driving vehicle's surrounding environment is crucial for its navigation system. To enhance the effectiveness of existing algorithms and facilitate further research, it is essential to provide…
Global contexts in images are quite valuable in image-to-image translation problems. Conventional attention-based and graph-based models capture the global context to a large extent, however, these are computationally expensive. Moreover,…
Autonomous driving systems face significant challenges in achieving human-like adaptability, robustness, and interpretability in complex, open-world environments. These challenges stem from fragmented architectures, limited generalization…
The capabilities of autonomous flight with unmanned aerial vehicles (UAVs) have significantly increased in recent times. However, basic problems such as fast and robust geo-localization in GPS-denied environments still remain unsolved.…
Autonomous vehicles demand detailed maps to maneuver reliably through traffic, which need to be kept up-to-date to ensure a safe operation. A promising way to adapt the maps to the ever-changing road-network is to use crowd-sourced data…
Drone-view geo-localization aims to match a query drone image, often captured under adverse weather conditions (e.g., rain, snow, fog), against a gallery of geo-tagged satellite images. Weather-induced degradations in the drone view, such…
Environment prediction frameworks are critical for the safe navigation of autonomous vehicles (AVs) in dynamic settings. LiDAR-generated occupancy grid maps (L-OGMs) offer a robust bird's-eye view for the scene representation, enabling…
Monocular 3D lane detection aims to estimate the 3D position of lanes from frontal-view (FV) images. However, existing methods are fundamentally constrained by the inherent ambiguity of single-frame input, which leads to inaccurate…
Adverse conditions like snow, rain, nighttime, and fog, pose challenges for autonomous driving perception systems. Existing methods have limited effectiveness in improving essential computer vision tasks, such as semantic segmentation, and…
Multi-view 3D visual grounding is critical for autonomous driving vehicles to interpret natural languages and localize target objects in complex environments. However, existing datasets and methods suffer from coarse-grained language…
Autonomous vehicles rely heavily upon their perception subsystems to see the environment in which they operate. Unfortunately, the effect of variable weather conditions presents a significant challenge to object detection algorithms, and…
Efficient relocalization is essential for intelligent vehicles when GPS reception is insufficient or sensor-based localization fails. Recent advances in Bird's-Eye-View (BEV) segmentation allow for accurate estimation of local scene…
Autonomous driving technology has the potential to transform transportation, but its wide adoption depends on the development of interpretable and transparent decision-making systems. Scene captioning, which generates natural language…
Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance degrades in high-resolution interfaces, where dense layouts and…
Large multimodal models (LMMs) excel in scene understanding but struggle with fine-grained spatiotemporal reasoning due to weak alignment between linguistic and visual representations. Existing methods map textual positions and durations…
The environmental perception of autonomous vehicles in normal conditions have achieved considerable success in the past decade. However, various unfavourable conditions such as fog, low-light, and motion blur will degrade image quality and…
Reliable segmentation of road lines and markings is critical to autonomous driving. Our work is motivated by the observations that road lines and markings are (1) frequently occluded in the presence of moving vehicles, shadow, and glare and…
Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…
Accurate and reliable spatial and motion information plays a pivotal role in autonomous driving systems. However, object-level perception models struggle with handling open scenario categories and lack precise intrinsic geometry. On the…
CLIP-based prompt tuning enables pretrained Vision-Language Models (VLMs) to efficiently adapt to downstream tasks. Although existing studies have made significant progress, they pay limited attention to changes in the internal attention…