paper-with-me

Papers Event-based Object Segmentation

“Event-based Object Segmentation” 태그가 달린 논문 8편 · 필터 해제

Segment Any Events via Weighted Adaptation of Pivotal Tokens

2023-12-24 · Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou 외

In this paper, we delve into the nuanced challenge of tailoring the Segment Anything Models (SAMs) for integration with event data, with the overarching objective of attaining robust and universal object segmentation wit…

Event-based Object Segmentation

Segment Anything

2023-04-05 · ICCV 2023 1 · Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 외

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with…

Event-based Object SegmentationImage SegmentationRobot Manipulation GeneralizationSegmentation+3

ESS: Learning Event-based Semantic Segmentation from Still Images

2022-03-18 · Zhaoning Sun, Nico Messikommer, Daniel Gehrig, Davide Scaramuzza

Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to a…

Domain AdaptationEvent-based Object SegmentationSegmentationSemantic Segmentation+1

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation

2021-11-24 · CVPR 2021 1 · Lin Wang, Yujeong Chae, Sung-Hoon Yoon, Tae-Kyun Kim 외

Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A hurdle of training event-based models i…

Event-based Object SegmentationKnowledge DistillationObject RecognitionSemantic Segmentation

Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation

2021-09-04 · ICCV 2021 10 · Lin Wang, Yujeong Chae, Kuk-Jin Yoon

Event cameras are novel sensors that perceive the per-pixel intensity changes and output asynchronous event streams with high dynamic range and less motion blur. It has been shown that events alone can be used for end-ta…

DecoderDepth EstimationEvent-based Object SegmentationRepresentation Learning+3

Event-Based Video Reconstruction Using Transformer

2021-01-01 · ICCV 2021 10 · Wenming Weng, Yueyi Zhang, Zhiwei Xiong

Event cameras, which output events by detecting spatio-temporal brightness changes, bring a novel paradigm to image sensors with high dynamic range and low latency. Previous works have achieved impressive performance…

Event-based Object SegmentationEvent-Based Video ReconstructionVideo Reconstruction

Learning to Exploit Multiple Vision Modalities by Using Grafted Networks

2020-03-24 · ECCV 2020 8 · Yuhuang Hu, Tobi Delbruck, Shih-Chii Liu

Novel vision sensors such as thermal, hyperspectral, polarization, and event cameras provide information that is not available from conventional intensity cameras. An obstacle to using these sensors with current powerful…

Event-based Object SegmentationGPUobject-detectionObject Detection

High Speed and High Dynamic Range Video with an Event Camera

2019-06-15 · Henri Rebecq, René Ranftl, Vladlen Koltun, Davide Scaramuzza

Event cameras are novel sensors that report brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with respect to conventional cameras: high te…

Event-based Object SegmentationVideo ReconstructionVocal Bursts Intensity Prediction
1–8 / 8