paper-with-me

Papers Video Shadow Detection

“Video Shadow Detection” 태그가 달린 논문 10편 · 필터 해제

When SAM2 Meets Video Shadow and Mirror Detection

2024-12-26 · Leiping Jie

As the successor to the Segment Anything Model (SAM), the Segment Anything Model 2 (SAM2) not only improves performance in image segmentation but also extends its capabilities to video segmentation. However, its effectiv…

Image SegmentationMirror DetectionSegmentationSemantic Segmentation+4

Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era

2024-09-03 · Xiaowei Hu, Zhenghao Xing, Tianyu Wang, Chi-Wing Fu 외

Shadows are created when light encounters obstacles, resulting in regions of reduced illumination. In computer vision, detecting, removing, and generating shadows are critical tasks for improving scene understanding, enh…

Scene UnderstandingShadow DetectionSurveyVideo Editing+1

Timeline and Boundary Guided Diffusion Network for Video Shadow Detection

2024-08-21 · Haipeng Zhou, Honqiu Wang, Tian Ye, Zhaohu Xing 외

Video Shadow Detection (VSD) aims to detect the shadow masks with frame sequence. Existing works suffer from inefficient temporal learning. Moreover, few works address the VSD problem by considering the characteristic (i…

Shadow DetectionVideo Shadow Detection

Language-Driven Interactive Shadow Detection

2024-08-16 · Hongqiu Wang, Wei Wang, Haipeng Zhou, Huihui Xu 외

Traditional shadow detectors often identify all shadow regions of static images or video sequences. This work presents the Referring Video Shadow Detection (RVSD), which is an innovative task that rejuvenates the classic…

DescriptiveShadow DetectionVideo EditingVideo Shadow Detection

Detect Any Shadow: Segment Anything for Video Shadow Detection

2023-05-26 · Yonghui Wang, Wengang Zhou, Yunyao Mao, Houqiang Li

Segment anything model (SAM) has achieved great success in the field of natural image segmentation. Nevertheless, SAM tends to consider shadows as background and therefore does not perform segmentation on them. In this p…

Image SegmentationSemantic SegmentationShadow DetectionVideo Shadow Detection

SCOTCH and SODA: A Transformer Video Shadow Detection Framework

2022-11-13 · CVPR 2023 1 · Lihao Liu, Jean Prost, Lei Zhu, Nicolas Papadakis 외

Shadows in videos are difficult to detect because of the large shadow deformation between frames. In this work, we argue that accounting for shadow deformation is essential when designing a video shadow detection method.…

Contrastive LearningShadow DetectionVideo Shadow Detection

Learning Shadow Correspondence for Video Shadow Detection

2022-07-30 · Xinpeng Ding, Jingweng Yang, Xiaowei Hu, Xiaomeng Li

Video shadow detection aims to generate consistent shadow predictions among video frames. However, the current approaches suffer from inconsistent shadow predictions across frames, especially when the illumination and ba…

Shadow DetectionVideo Shadow Detection

Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training

2022-06-17 · CVPR 2022 1 · Xiao Lu, Yihong Cao, Sheng Liu, Chengjiang Long 외

It is challenging to annotate large-scale datasets for supervised video shadow detection methods. Using a model trained on labeled images to the video frames directly may lead to high generalization error and temporal in…

Shadow DetectionSpatial InterpolationVideo Shadow Detection

Temporal Feature Warping for Video Shadow Detection

2021-07-29 · Shilin Hu, Hieu Le, Dimitris Samaras

While single image shadow detection has been improving rapidly in recent years, video shadow detection remains a challenging task due to data scarcity and the difficulty in modelling temporal consistency. The current vid…

Optical Flow EstimationShadow DetectionVideo Shadow Detection

Triple-cooperative Video Shadow Detection

2021-03-11 · CVPR 2021 1 · Zhihao Chen, Liang Wan, Lei Zhu, Jia Shen 외

Shadow detection in a single image has received significant research interest in recent years. However, much fewer works have been explored in shadow detection over dynamic scenes. The bottleneck is the lack of a well-es…

Saliency DetectionSemantic SegmentationShadow DetectionVideo Object Segmentation+2
1–10 / 10