Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319302572> ?p ?o ?g. }
- W4319302572 endingPage "9503" @default.
- W4319302572 startingPage "9486" @default.
- W4319302572 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 <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>content-aware warping</i> , 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. The source code is publicly available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/MantangGuo/CW4VS</uri> ." @default.
- W4319302572 created "2023-02-07" @default.
- W4319302572 creator A5031957432 @default.
- W4319302572 creator A5035422552 @default.
- W4319302572 creator A5067895271 @default.
- W4319302572 creator A5077387004 @default.
- W4319302572 creator A5083714878 @default.
- W4319302572 creator A5090079801 @default.
- W4319302572 date "2023-08-01" @default.
- W4319302572 modified "2023-10-02" @default.
- W4319302572 title "Content-Aware Warping for View Synthesis" @default.
- W4319302572 cites W1557438097 @default.
- W4319302572 cites W1951771206 @default.
- W4319302572 cites W1971719398 @default.
- W4319302572 cites W1997057955 @default.
- W4319302572 cites W2026058811 @default.
- W4319302572 cites W2042687553 @default.
- W4319302572 cites W2051929895 @default.
- W4319302572 cites W2055397548 @default.
- W4319302572 cites W2063366997 @default.
- W4319302572 cites W2067827172 @default.
- W4319302572 cites W2119967924 @default.
- W4319302572 cites W2129404737 @default.
- W4319302572 cites W2133665775 @default.
- W4319302572 cites W2138821028 @default.
- W4319302572 cites W2140950877 @default.
- W4319302572 cites W2150007820 @default.
- W4319302572 cites W2194775991 @default.
- W4319302572 cites W2200825767 @default.
- W4319302572 cites W2239879258 @default.
- W4319302572 cites W2257183329 @default.
- W4319302572 cites W2290439950 @default.
- W4319302572 cites W2338968644 @default.
- W4319302572 cites W2471962767 @default.
- W4319302572 cites W2551052086 @default.
- W4319302572 cites W2554759989 @default.
- W4319302572 cites W2608225500 @default.
- W4319302572 cites W2612645170 @default.
- W4319302572 cites W2738449271 @default.
- W4319302572 cites W2738551266 @default.
- W4319302572 cites W2744570394 @default.
- W4319302572 cites W2758175304 @default.
- W4319302572 cites W2895191479 @default.
- W4319302572 cites W2895527865 @default.
- W4319302572 cites W2897594148 @default.
- W4319302572 cites W2901982540 @default.
- W4319302572 cites W2914600502 @default.
- W4319302572 cites W2943445277 @default.
- W4319302572 cites W2949258649 @default.
- W4319302572 cites W2949362021 @default.
- W4319302572 cites W2949657144 @default.
- W4319302572 cites W2957926190 @default.
- W4319302572 cites W2962793285 @default.
- W4319302572 cites W2963557767 @default.
- W4319302572 cites W2963872754 @default.
- W4319302572 cites W2964288609 @default.
- W4319302572 cites W2978701653 @default.
- W4319302572 cites W2990256309 @default.
- W4319302572 cites W3034462356 @default.
- W4319302572 cites W3034801905 @default.
- W4319302572 cites W3089028664 @default.
- W4319302572 cites W3109244019 @default.
- W4319302572 cites W3167914619 @default.
- W4319302572 cites W3171236455 @default.
- W4319302572 cites W3176368002 @default.
- W4319302572 cites W3180808523 @default.
- W4319302572 cites W3186630079 @default.
- W4319302572 cites W3193453419 @default.
- W4319302572 doi "https://doi.org/10.1109/tpami.2023.3242709" @default.
- W4319302572 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37022422" @default.
- W4319302572 hasPublicationYear "2023" @default.
- W4319302572 type Work @default.
- W4319302572 citedByCount "1" @default.
- W4319302572 countsByYear W43193025722023 @default.
- W4319302572 crossrefType "journal-article" @default.
- W4319302572 hasAuthorship W4319302572A5031957432 @default.
- W4319302572 hasAuthorship W4319302572A5035422552 @default.
- W4319302572 hasAuthorship W4319302572A5067895271 @default.
- W4319302572 hasAuthorship W4319302572A5077387004 @default.
- W4319302572 hasAuthorship W4319302572A5083714878 @default.
- W4319302572 hasAuthorship W4319302572A5090079801 @default.
- W4319302572 hasBestOaLocation W43193025722 @default.
- W4319302572 hasConcept C111919701 @default.
- W4319302572 hasConcept C115961682 @default.
- W4319302572 hasConcept C137800194 @default.
- W4319302572 hasConcept C153180895 @default.
- W4319302572 hasConcept C154945302 @default.
- W4319302572 hasConcept C157202957 @default.
- W4319302572 hasConcept C160633673 @default.
- W4319302572 hasConcept C205711294 @default.
- W4319302572 hasConcept C2776449333 @default.
- W4319302572 hasConcept C31972630 @default.
- W4319302572 hasConcept C41008148 @default.
- W4319302572 hasConcept C43126263 @default.
- W4319302572 hasConceptScore W4319302572C111919701 @default.
- W4319302572 hasConceptScore W4319302572C115961682 @default.
- W4319302572 hasConceptScore W4319302572C137800194 @default.
- W4319302572 hasConceptScore W4319302572C153180895 @default.