English
Related papers

Related papers: Agent-Centric Observation Adaptation for Robust Vi…

200 papers

The robustness of object detection algorithms plays a prominent role in real-world applications, especially in uncontrolled environments due to distortions during image acquisition. It has been proven that the performance of object…

Computer Vision and Pattern Recognition · Computer Science 2022-10-31 Ayman Beghdadi , Malik Mallem , Lotfi Beji

Detecting objects reliably under extreme low-light conditions is an open problem in computer vision, with practical urgency in applications ranging from nighttime surveillance to search-and-rescue robotics. Conventional RGB cameras degrade…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Raju Imandi , Chethana B , Bharatesh Chakravarthi , Yong-Guk Kim , Manipriya S , Pavan Kumar B N

MoCo is effective for unsupervised image representation learning. In this paper, we propose VideoMoCo for unsupervised video representation learning. Given a video sequence as an input sample, we improve the temporal feature representations…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Tian Pan , Yibing Song , Tianyu Yang , Wenhao Jiang , Wei Liu

Existing Infrared and Visible Image Fusion (IVIF) methods typically assume high-quality inputs. However, when handing degraded images, these methods heavily rely on manually switching between different pre-processing techniques. This…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Tianpei Zhang , Jufeng Zhao , Yiming Zhu , Guangmang Cui

Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to…

Computer Vision and Pattern Recognition · Computer Science 2024-02-26 Leon Sick , Dominik Engel , Pedro Hermosilla , Timo Ropinski

Masked autoencoder has demonstrated its effectiveness in self-supervised point cloud learning. Considering that masking is a kind of corruption, in this work we explore a more general denoising autoencoder for point cloud learning…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Yabin Zhang , Jiehong Lin , Ruihuang Li , Kui Jia , Lei Zhang

We propose a margin-based loss for tuning joint vision-language models so that their gradient-based explanations are consistent with region-level annotations provided by humans for relatively smaller grounding datasets. We refer to this…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Ziyan Yang , Kushal Kafle , Franck Dernoncourt , Vicente Ordonez

GAN-based image compression schemes have shown remarkable progress lately due to their high perceptual quality at low bit rates. However, there are two main issues, including 1) the reconstructed image perceptual degeneration in color,…

Image and Video Processing · Electrical Eng. & Systems 2023-06-21 Fanxin Xia , Jian Jin , Lili Meng , Feng Ding , Huaxiang Zhang

Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradation-Aware Adaptive Context Gating), which enables explicit perception of degradation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Lei He , Jielei Chu , Fengmao Lv , Weide Liu , Tianrui Li , Jun Cheng , Yuming Fang

Object detectors achieve strong performance under nominal imaging conditions but can fail silently when exposed to blur, noise, compression, adverse weather, or resolution changes. In safety-critical settings, it is therefore insufficient…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Stefan Becker , Simon Weiss , Wolfgang Hübner , Michael Arens

Dynamic vision sensors (DVS) are bio-inspired devices that capture visual information in the form of asynchronous events, which encode changes in pixel intensity with high temporal resolution and low latency. These events provide rich…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Jingkai Sun , Qiang Zhang , Jiaxu Wang , Jiahang Cao , Renjing Xu

We provide a framework for solving inverse problems with diffusion models learned from linearly corrupted data. Firstly, we extend the Ambient Diffusion framework to enable training directly from measurements corrupted in the Fourier…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Asad Aali , Giannis Daras , Brett Levac , Sidharth Kumar , Alexandros G. Dimakis , Jonathan I. Tamir

Restoring images degraded by adverse weather remains a significant challenge due to the highly non-uniform and spatially heterogeneous nature of weather-induced artifacts, e.g., fine-grained rain streaks versus widespread haze. Accurately…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Hainuo Wang , Qiming Hu , Xiaojie Guo

Today's robots often interface with data-driven perception and planning models with classical model-predictive controllers (MPC). Often, such learned perception/planning models produce erroneous waypoint predictions on out-of-distribution…

Robotics · Computer Science 2022-12-06 Shubhankar Agarwal , Sandeep P. Chinchali

DRIVE-C is a controlled corruption dataset designed to evaluate visual perception robustness in autonomous driving systems. It is built from real-world forward-facing driving videos collected across daytime, nighttime, urban, rural,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Shiva Aher

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

Multiagent Systems · Computer Science 2026-03-18 Churong Liang , Jinling Gan , Kairan Hong , Qiushi Tian , Zongze Wu , Runnan Li

The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. This paper offers the first comprehensive study on robust PVOS…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Sohyun Lee , Yeho Gwon , Lukas Hoyer , Konrad Schindler , Christos Sakaridis , Suha Kwak

In industrial vision, the anomaly detection problem can be addressed with an autoencoder trained to map an arbitrary image, i.e. with or without any defect, to a clean image, i.e. without any defect. In this approach, anomaly detection…

Image and Video Processing · Electrical Eng. & Systems 2020-11-05 Anne-Sophie Collin , Christophe De Vleeschouwer

Audio-visual speech recognition (AVSR) incorporates auditory and visual modalities to improve recognition accuracy, particularly in noisy environments where audio-only speech systems are insufficient. While previous research has largely…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-01 Sungnyun Kim , Sungwoo Cho , Sangmin Bae , Kangwook Jang , Se-Young Yun

Vision-based control relies on accurate perception to achieve robustness. However, image distribution changes caused by sensor noise, adverse weather, and dynamic lighting can degrade perception, leading to suboptimal control decisions.…

Robotics · Computer Science 2025-08-01 Carson Sobolewski , Zhenjiang Mao , Kshitij Maruti Vejre , Ivan Ruchkin