Related papers: JarvisIR: Elevating Autonomous Driving Perception …

Unmanned Aerial Vehicles (UAV) have been standing out due to the wide range of applications in which they can be used autonomously. However, they need intelligent systems capable of providing a greater understanding of what they perceive to…

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…

Autonomous driving systems often infer pedestrian yielding behavior from geometric and kinematic cues alone, limiting their ability to reason about visual scene context and age-dependent behavioral variability. This limitation can produce…

Accurate environmental perception is critical for advanced driver assistance systems (ADAS). Light detection and ranging (LiDAR) systems play a crucial role in ADAS; they can reliably detect obstacles and help ensure traffic safety.…

Unsupervised image restoration under multi-weather conditions remains a fundamental yet underexplored challenge. While existing methods often rely on task-specific physical priors, their narrow focus limits scalability and generalization to…

Selective prediction minimizes incorrect predictions from vision-language models (VLMs) by allowing them to abstain from answering when uncertain. However, when deploying a vision-language system with low tolerance for inaccurate…

Image restoration (IR) in real-world scenarios presents significant challenges due to the lack of high-capacity models and comprehensive datasets. To tackle these issues, we present a dual strategy: GenIR, an innovative data curation…

Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform visual reasoning as opposed to relying on linguistic priors…

While deep learning-based weather forecasting paradigms have made significant strides, addressing extreme weather diagnostics remains a formidable challenge. This gap exists primarily because the diagnostic process demands sophisticated…

A purposely built deep learning algorithm for the Verification of Earth-System ParametERisation (VESPER) is used to assess recent upgrades of the global physiographic datasets underpinning the quality of the Integrated Forecasting System…

Geoscience intelligence is expected to understand, reason about, and predict earth system changes to support human decision-making in critical domains such as disaster response, climate adaptation and environmental protection. Although…

Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples. Existing solutions, such as retraining or fine-tuning on…

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning…

Rendering realistic images from 3D reconstruction is an essential task of many Computer Vision and Robotics pipelines, notably for mixed-reality applications as well as training autonomous agents in simulated environments. However, the…

Autonomous vehicles face major perception and navigation challenges in adverse weather such as rain, fog, and snow, which degrade the performance of LiDAR, RADAR, and RGB camera sensors. While each sensor type offers unique strengths, such…

Robotic manipulation requires sophisticated commonsense reasoning, a capability naturally possessed by large-scale Vision-Language Models (VLMs). While VLMs show promise as zero-shot planners, their lack of grounded physical understanding…

Vision-language models (VLMs) excel at descriptive tasks, but whether they truly understand scenes from visual observations remains uncertain. We introduce IR3D-Bench, a benchmark challenging VLMs to demonstrate understanding through active…

Video generative models trained on expert demonstrations have been utilized as performant text-conditioned visual planners for solving robotic tasks. However, generalization to unseen tasks remains a challenge. Whereas improved…

Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination…

Humans rely on the synergistic control of head (cephalomotor) and eye (oculomotor) to efficiently search for visual information in 360{\deg}. However, prior approaches to visual search are limited to a static image, neglecting the physical…