paper-with-me

홈 › Papers

Examining Autoexposure for Challenging Scenes

2023-09-08 · ICCV 2023 1 · SaiKiran Tedla, Beixuan Yang, Michael S. Brown

Autoexposure (AE) is a critical step applied by camera systems to ensure properly exposed images. While current AE algorithms are effective in well-lit environments with constant illumination, these algorithms still struggle in environments with bright light sources or scenes with abrupt changes in lighting. A significant hurdle in developing new AE algorithms for challenging environments, especially those with time-varying lighting, is the lack of suitable image datasets. To address this issue, we have captured a new 4D exposure dataset that provides a large solution space (i.e., shutter speed range from (1/500 to 15 seconds) over a temporal sequence with moving objects, bright lights, and varying lighting. In addition, we have designed a software platform to allow AE algorithms to be used in a plug-and-play manner with the dataset. Our dataset and associate platform enable repeatable evaluation of different AE algorithms and provide a much-needed starting point to develop better AE methods. We examine several existing AE strategies using our dataset and show that most users prefer a simple saliency method for challenging lighting conditions.

📄 PDF Abstract BibTeX arXiv:2309.04542

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

AE An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding

2024-01-17 · Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang 외

3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, gro…

3D visual groundingScene UnderstandingVisual Grounding

Adversarial Scene Reconstruction and Object Detection System for Assisting Autonomous Vehicle

2021-10-13 · Md Foysal Haque, Hay-Youn Lim, Dae-Seong Kang

In the current computer vision era classifying scenes through video surveillance systems is a crucial task. Artificial Intelligence (AI) Video Surveillance technologies have been advanced remarkably while artificial inte…

Deep Learningobject-detectionObject DetectionScene Understanding

Self Supervised Clustering of Traffic Scenes using Graph Representations

2022-11-24 · Maximilian Zipfl, Moritz Jarosch, J. Marius Zöllner

Examining graphs for similarity is a well-known challenge, but one that is mandatory for grouping graphs together. We present a data-driven method to cluster traffic scenes that is self-supervised, i.e. without manual la…

ClusteringGraph Embedding

Online Overexposed Pixels Hallucination in Videos with Adaptive Reference Frame Selection

2023-08-29 · Yazhou Xing, Amrita Mazumdar, Anjul Patney, Chao Liu 외

Low dynamic range (LDR) cameras cannot deal with wide dynamic range inputs, frequently leading to local overexposure issues. We present a learning-based system to reduce these artifacts without resorting to complex acqui…

Hallucination

Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes

2008-12-01 · NeurIPS 2008 12 · Erik B. Sudderth, Michael. I. Jordan

We develop a statistical framework for the simultaneous, unsupervised segmentation and discovery of visual object categories from image databases. Examining a large set of manually segmented scenes, we use chi--square te…

Gaussian ProcessesSegmentation