Please use this identifier to cite or link to this item:
https://repository.cihe.edu.hk/jspui/handle/cihe/4448
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Hui | en_US |
dc.contributor.other | Guo, M. | - |
dc.contributor.other | Hou, J. | - |
dc.contributor.other | Jin, J. | - |
dc.contributor.other | Zeng, H. | - |
dc.contributor.other | Lu, J. | - |
dc.date.accessioned | 2024-04-10T06:06:54Z | - |
dc.date.available | 2024-04-10T06:06:54Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | https://repository.cihe.edu.hk/jspui/handle/cihe/4448 | - |
dc.description.abstract | Existing image-based rendering methods usually adopt depth-based image warping operation to synthesize novel views. In this paper, we reason the essential limitations of the traditional warping operation to be the limited neighborhood and only distance-based interpolation weights. To this end, we propose content-aware warping , which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network. Based on this learnable warping module, we propose a new end-to-end learning-based framework for novel view synthesis from a set of input source views, in which two additional modules, namely confidence-based blending and feature-assistant spatial refinement, are naturally proposed to handle the occlusion issue and capture the spatial correlation among pixels of the synthesized view, respectively. Besides, we also propose a weight-smoothness loss term to regularize the network. Experimental results on light field datasets with wide baselines and multi-view datasets show that the proposed method significantly outperforms state-of-the-art methods both quantitatively and visually. | en_US |
dc.language.iso | en | en_US |
dc.publisher | IEEE | en_US |
dc.relation.ispartof | IEEE Transactions on Pattern Analysis and Machine Intelligence | en_US |
dc.title | Content-aware warping for view synthesis | en_US |
dc.type | journal article | en_US |
dc.identifier.doi | 10.1109/TPAMI.2023.3242709 | - |
dc.contributor.affiliation | School of Computing and Information Sciences | en_US |
dc.relation.issn | 1939-3539 | en_US |
dc.description.volume | 45 | en_US |
dc.description.issue | 8 | en_US |
dc.description.startpage | 9486 | en_US |
dc.description.endpage | 9503 | en_US |
dc.cihe.affiliated | Yes | - |
item.languageiso639-1 | en | - |
item.fulltext | No Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_6501 | - |
item.cerifentitytype | Publications | - |
item.openairetype | journal article | - |
item.grantfulltext | none | - |
crisitem.author.dept | Yam Pak Charitable Foundation School of Computing and Information Sciences | - |
Appears in Collections: | CIS Publication |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.