Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387448075> ?p ?o ?g. }
- W4387448075 endingPage "5622" @default.
- W4387448075 startingPage "5610" @default.
- W4387448075 abstract "In this paper, we explore the problem of 3D point cloud representation-based view synthesis from a set of sparse source views. To tackle this challenging problem, we propose a new deep learning-based view synthesis paradigm that learns a locally unified 3D point cloud from source views. Specifically, we first construct sub-point clouds by projecting source views to 3D space based on their depth maps. Then, we learn the locally unified 3D point cloud by adaptively fusing points at a local neighborhood defined on the union of the sub-point clouds. Besides, we also propose a 3D geometry-guided image restoration module to fill the holes and recover high-frequency details of the rendered novel views. Experimental results on three benchmark datasets demonstrate that our method can improve the average PSNR by more than 4 dB while preserving more accurate visual details, compared with state-of-the-art view synthesis methods. The code will be publicly available at https://github.com/mengyou2/PCVS." @default.
- W4387448075 created "2023-10-10" @default.
- W4387448075 creator A5005147528 @default.
- W4387448075 creator A5031957432 @default.
- W4387448075 creator A5061594020 @default.
- W4387448075 creator A5067895271 @default.
- W4387448075 creator A5077387004 @default.
- W4387448075 date "2023-01-01" @default.
- W4387448075 modified "2023-10-15" @default.
- W4387448075 title "Learning A Locally Unified 3D Point Cloud for View Synthesis" @default.
- W4387448075 cites W1971719398 @default.
- W4387448075 cites W2028687412 @default.
- W4387448075 cites W2044618760 @default.
- W4387448075 cites W2063366997 @default.
- W4387448075 cites W2081078589 @default.
- W4387448075 cites W2238402354 @default.
- W4387448075 cites W2294015878 @default.
- W4387448075 cites W2294985758 @default.
- W4387448075 cites W2338968644 @default.
- W4387448075 cites W2342277278 @default.
- W4387448075 cites W2348664362 @default.
- W4387448075 cites W2531849700 @default.
- W4387448075 cites W2598591334 @default.
- W4387448075 cites W2738551266 @default.
- W4387448075 cites W2758175304 @default.
- W4387448075 cites W2883907768 @default.
- W4387448075 cites W2895191479 @default.
- W4387448075 cites W2907750714 @default.
- W4387448075 cites W2943445277 @default.
- W4387448075 cites W2949657144 @default.
- W4387448075 cites W2949825757 @default.
- W4387448075 cites W2951881930 @default.
- W4387448075 cites W2957926190 @default.
- W4387448075 cites W2962785568 @default.
- W4387448075 cites W2962793285 @default.
- W4387448075 cites W2963557767 @default.
- W4387448075 cites W2964288609 @default.
- W4387448075 cites W2968257580 @default.
- W4387448075 cites W2981542933 @default.
- W4387448075 cites W2982966540 @default.
- W4387448075 cites W2985299701 @default.
- W4387448075 cites W2990256309 @default.
- W4387448075 cites W3012494314 @default.
- W4387448075 cites W3034528136 @default.
- W4387448075 cites W3035318263 @default.
- W4387448075 cites W3035524985 @default.
- W4387448075 cites W3105863736 @default.
- W4387448075 cites W3108066358 @default.
- W4387448075 cites W3108325989 @default.
- W4387448075 cites W3109244019 @default.
- W4387448075 cites W3109376949 @default.
- W4387448075 cites W3109585842 @default.
- W4387448075 cites W3167914619 @default.
- W4387448075 cites W3172568571 @default.
- W4387448075 cites W3176368002 @default.
- W4387448075 cites W3177583232 @default.
- W4387448075 cites W3180808523 @default.
- W4387448075 cites W3186630079 @default.
- W4387448075 cites W3202343472 @default.
- W4387448075 cites W3204859697 @default.
- W4387448075 cites W4214628039 @default.
- W4387448075 cites W4286615883 @default.
- W4387448075 cites W4288242633 @default.
- W4387448075 cites W4312546206 @default.
- W4387448075 cites W4312706422 @default.
- W4387448075 cites W4312970120 @default.
- W4387448075 doi "https://doi.org/10.1109/tip.2023.3321458" @default.
- W4387448075 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37812537" @default.
- W4387448075 hasPublicationYear "2023" @default.
- W4387448075 type Work @default.
- W4387448075 citedByCount "0" @default.
- W4387448075 crossrefType "journal-article" @default.
- W4387448075 hasAuthorship W4387448075A5005147528 @default.
- W4387448075 hasAuthorship W4387448075A5031957432 @default.
- W4387448075 hasAuthorship W4387448075A5061594020 @default.
- W4387448075 hasAuthorship W4387448075A5067895271 @default.
- W4387448075 hasAuthorship W4387448075A5077387004 @default.
- W4387448075 hasConcept C108583219 @default.
- W4387448075 hasConcept C111919701 @default.
- W4387448075 hasConcept C131979681 @default.
- W4387448075 hasConcept C13280743 @default.
- W4387448075 hasConcept C154945302 @default.
- W4387448075 hasConcept C177264268 @default.
- W4387448075 hasConcept C17744445 @default.
- W4387448075 hasConcept C185798385 @default.
- W4387448075 hasConcept C199360897 @default.
- W4387448075 hasConcept C199539241 @default.
- W4387448075 hasConcept C205649164 @default.
- W4387448075 hasConcept C205711294 @default.
- W4387448075 hasConcept C2524010 @default.
- W4387448075 hasConcept C2776359362 @default.
- W4387448075 hasConcept C2776449333 @default.
- W4387448075 hasConcept C2776760102 @default.
- W4387448075 hasConcept C2780801425 @default.
- W4387448075 hasConcept C28719098 @default.
- W4387448075 hasConcept C31972630 @default.
- W4387448075 hasConcept C33923547 @default.
- W4387448075 hasConcept C41008148 @default.