FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972258980> ?p ?o ?g. }

• W2972258980 abstract "We present an approach that learns to synthesize high-quality, novel views of 3D objects or scenes, while providing fine-grained and precise control over the 6-DOF viewpoint. The approach is self-supervised and only requires 2D images and associated view transforms for training. Our main contribution is a network architecture that leverages a transforming auto-encoder in combination with a depth-guided warping procedure to predict geometrically accurate unseen views. Leveraging geometric constraints renders direct supervision via depth or flow maps unnecessary. If large parts of the object are occluded in the source view, a purely learning based prior is used to predict the values for dis-occluded pixels. Our network furthermore predicts a per-pixel mask, used to fuse depth-guided and pixel-based predictions. The resulting images reflect the desired 6-DOF transformation and details are preserved. We thoroughly evaluate our architecture on synthetic and real scenes and under fine-grained and fixed-view settings. Finally, we demonstrate that the approach generalizes to entirely unseen images such as product images downloaded from the internet." @default.
• W2972258980 created "2019-09-12" @default.
• W2972258980 creator A5025000908 @default.
• W2972258980 creator A5047371218 @default.
• W2972258980 creator A5089838274 @default.
• W2972258980 date "2019-01-07" @default.
• W2972258980 modified "2023-09-26" @default.
• W2972258980 title "Monocular Neural Image Based Rendering with Continuous View Control" @default.
• W2972258980 cites W1677409904 @default.
• W2972258980 cites W1686810756 @default.
• W2972258980 cites W1691728462 @default.
• W2972258980 cites W1776042733 @default.
• W2972258980 cites W1920022804 @default.
• W2972258980 cites W1959608418 @default.
• W2972258980 cites W1971719398 @default.
• W2972258980 cites W1992178727 @default.
• W2972258980 cites W2028687412 @default.
• W2972258980 cites W2063366997 @default.
• W2972258980 cites W2063878429 @default.
• W2972258980 cites W2066763472 @default.
• W2972258980 cites W2099471712 @default.
• W2972258980 cites W2111169574 @default.
• W2972258980 cites W2119781527 @default.
• W2972258980 cites W2130630796 @default.
• W2972258980 cites W2133665775 @default.
• W2972258980 cites W2140950877 @default.
• W2972258980 cites W2150066425 @default.
• W2972258980 cites W2151819132 @default.
• W2972258980 cites W2160014001 @default.
• W2972258980 cites W2171740948 @default.
• W2972258980 cites W2188956040 @default.
• W2972258980 cites W2190691619 @default.
• W2972258980 cites W2263714001 @default.
• W2972258980 cites W2267877820 @default.
• W2972258980 cites W2273818272 @default.
• W2972258980 cites W2294985758 @default.
• W2972258980 cites W2331128040 @default.
• W2972258980 cites W2342277278 @default.
• W2972258980 cites W2348664362 @default.
• W2972258980 cites W2474281075 @default.
• W2972258980 cites W2495603374 @default.
• W2972258980 cites W2518780089 @default.
• W2972258980 cites W2555437177 @default.
• W2972258980 cites W2556802233 @default.
• W2972258980 cites W2560722161 @default.
• W2972258980 cites W2598591334 @default.
• W2972258980 cites W2605498834 @default.
• W2972258980 cites W2606533435 @default.
• W2972258980 cites W2609883120 @default.
• W2972258980 cites W2753738274 @default.
• W2972258980 cites W2758175304 @default.
• W2972258980 cites W2785994986 @default.
• W2972258980 cites W2883907768 @default.
• W2972258980 cites W2889582485 @default.
• W2972258980 cites W2893749619 @default.
• W2972258980 cites W2895191479 @default.
• W2972258980 cites W2897594148 @default.
• W2972258980 cites W2901982540 @default.
• W2972258980 cites W2903200123 @default.
• W2972258980 cites W2910764989 @default.
• W2972258980 cites W2933283236 @default.
• W2972258980 cites W2936824929 @default.
• W2972258980 cites W2943445277 @default.
• W2972258980 cites W2949657144 @default.
• W2972258980 cites W2951179855 @default.
• W2972258980 cites W2951880955 @default.
• W2972258980 cites W2952809312 @default.
• W2972258980 cites W2962770929 @default.
• W2972258980 cites W2963026643 @default.
• W2972258980 cites W2963073614 @default.
• W2972258980 cites W2963226019 @default.
• W2972258980 cites W2963475767 @default.
• W2972258980 cites W2963527086 @default.
• W2972258980 cites W2963557767 @default.
• W2972258980 cites W2963604457 @default.
• W2972258980 cites W2963703618 @default.
• W2972258980 cites W2963739349 @default.
• W2972258980 cites W2963749150 @default.
• W2972258980 cites W2963869461 @default.
• W2972258980 cites W2963872754 @default.
• W2972258980 cites W2963966978 @default.
• W2972258980 cites W2964121028 @default.
• W2972258980 cites W2964137676 @default.
• W2972258980 cites W2964288609 @default.
• W2972258980 cites W2966661 @default.
• W2972258980 cites W2968257580 @default.
• W2972258980 cites W603908379 @default.
• W2972258980 doi "https://doi.org/10.48550/arxiv.1901.01880" @default.
• W2972258980 hasPublicationYear "2019" @default.
• W2972258980 type Work @default.
• W2972258980 sameAs 2972258980 @default.
• W2972258980 citedByCount "9" @default.
• W2972258980 countsByYear W29722589802019 @default.
• W2972258980 countsByYear W29722589802020 @default.
• W2972258980 countsByYear W29722589802021 @default.
• W2972258980 crossrefType "posted-content" @default.
• W2972258980 hasAuthorship W2972258980A5025000908 @default.
• W2972258980 hasAuthorship W2972258980A5047371218 @default.
• W2972258980 hasAuthorship W2972258980A5089838274 @default.
• W2972258980 hasBestOaLocation W29722589801 @default.

• next