Triplane-Smoothed Video Dehazing with CLIP-Enhanced Generalization

Guardado en:
Detalles Bibliográficos
Publicado en:International Journal of Computer Vision vol. 133, no. 1 (Jan 2025), p. 475
Publicado:
Springer Nature B.V.
Materias:
Acceso en línea:Citation/Abstract
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3152332148
003 UK-CbPIL
022 |a 0920-5691 
022 |a 1573-1405 
024 7 |a 10.1007/s11263-024-02161-0  |2 doi 
035 |a 3152332148 
045 2 |b d20250101  |b d20250131 
084 |a 175340  |2 nlm 
245 1 |a Triplane-Smoothed Video Dehazing with CLIP-Enhanced Generalization 
260 |b Springer Nature B.V.  |c Jan 2025 
513 |a Journal Article 
520 3 |a Video dehazing is a critical research area in computer vision that aims to enhance the quality of hazy frames, which benefits many downstream tasks, e.g. semantic segmentation. Recent work devise CNN-based structure or attention mechanism to fuse temporal information, while some others utilize offset between frames to align frames explicitly. Another significant line of video dehazing research focuses on constructing paired datasets by synthesizing foggy effect on clear video or generating real haze effect on indoor scenes. Despite the significant contributions of these dehazing networks and datasets to the advancement of video dehazing, current methods still suffer from spatial–temporal inconsistency and poor generalization ability. We address the aforementioned issues by proposing a triplane smoothing module to explicitly benefit from spatial–temporal smooth prior of the input video and generate temporally coherent dehazing results. We further devise a query base decoder to extract haze-relevant information while also aggregate temporal clues implicitly. To increase the generalization ability of our dehazing model we utilize CLIP guidance with a rich and high-level understanding of hazy effect. We conduct extensive experiments to verify the effectiveness of our model to generate spatial–temporally consistent dehazing results and produce pleasing dehazing results of real-world data. 
653 |a Datasets 
653 |a Computer vision 
653 |a Semantic segmentation 
653 |a Frames (data processing) 
653 |a Spatiotemporal data 
653 |a Spatial smoothing 
653 |a Haze 
653 |a Data smoothing 
653 |a Methods 
653 |a Queries 
773 0 |t International Journal of Computer Vision  |g vol. 133, no. 1 (Jan 2025), p. 475 
786 0 |d ProQuest  |t ABI/INFORM Global 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3152332148/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3152332148/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch