Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904383797> ?p ?o ?g. }
- W2904383797 abstract "With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learning-based 3D reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose Occupancy Networks, a new representation for learning-based 3D reconstruction methods. Occupancy networks implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier. In contrast to existing approaches, our representation encodes a description of the 3D output at infinite resolution without excessive memory footprint. We validate that our representation can efficiently encode 3D structure and can be inferred from various kinds of input. Our experiments demonstrate competitive results, both qualitatively and quantitatively, for the challenging tasks of 3D reconstruction from single images, noisy point clouds and coarse discrete voxel grids. We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks." @default.
- W2904383797 created "2018-12-22" @default.
- W2904383797 creator A5000291599 @default.
- W2904383797 creator A5016606943 @default.
- W2904383797 creator A5055590646 @default.
- W2904383797 creator A5072305321 @default.
- W2904383797 creator A5088795883 @default.
- W2904383797 date "2018-12-10" @default.
- W2904383797 modified "2023-10-05" @default.
- W2904383797 title "Occupancy Networks: Learning 3D Reconstruction in Function Space" @default.
- W2904383797 cites W1521328770 @default.
- W2904383797 cites W1583399309 @default.
- W2904383797 cites W1845536947 @default.
- W2904383797 cites W1920022804 @default.
- W2904383797 cites W1959608418 @default.
- W2904383797 cites W1966634937 @default.
- W2904383797 cites W1991113069 @default.
- W2904383797 cites W1992642990 @default.
- W2904383797 cites W2008073424 @default.
- W2904383797 cites W2009422376 @default.
- W2904383797 cites W2027947870 @default.
- W2904383797 cites W2053825465 @default.
- W2904383797 cites W2074954154 @default.
- W2904383797 cites W2078000663 @default.
- W2904383797 cites W2099471712 @default.
- W2904383797 cites W2101744775 @default.
- W2904383797 cites W2112594540 @default.
- W2904383797 cites W2115579991 @default.
- W2904383797 cites W2121535648 @default.
- W2904383797 cites W2137610415 @default.
- W2904383797 cites W2146599206 @default.
- W2904383797 cites W2155343350 @default.
- W2904383797 cites W2167141871 @default.
- W2904383797 cites W2174133987 @default.
- W2904383797 cites W2190691619 @default.
- W2904383797 cites W2194775991 @default.
- W2904383797 cites W2211722331 @default.
- W2904383797 cites W2229412420 @default.
- W2904383797 cites W2229637417 @default.
- W2904383797 cites W2254644702 @default.
- W2904383797 cites W2342277278 @default.
- W2904383797 cites W2411541852 @default.
- W2904383797 cites W2511691466 @default.
- W2904383797 cites W2546066744 @default.
- W2904383797 cites W2556802233 @default.
- W2904383797 cites W2558748708 @default.
- W2904383797 cites W2559882727 @default.
- W2904383797 cites W2560609797 @default.
- W2904383797 cites W2560722161 @default.
- W2904383797 cites W2582734987 @default.
- W2904383797 cites W2594727217 @default.
- W2904383797 cites W2603429625 @default.
- W2904383797 cites W2606840594 @default.
- W2904383797 cites W2748512037 @default.
- W2904383797 cites W2767503796 @default.
- W2904383797 cites W2779856146 @default.
- W2904383797 cites W2784996692 @default.
- W2904383797 cites W2798314605 @default.
- W2904383797 cites W2798670728 @default.
- W2904383797 cites W2798856139 @default.
- W2904383797 cites W2876993306 @default.
- W2904383797 cites W2883221003 @default.
- W2904383797 cites W2890382763 @default.
- W2904383797 cites W2891624360 @default.
- W2904383797 cites W2902435637 @default.
- W2904383797 cites W2909750748 @default.
- W2904383797 cites W2913225681 @default.
- W2904383797 cites W2913581875 @default.
- W2904383797 cites W2914390273 @default.
- W2904383797 cites W2949130266 @default.
- W2904383797 cites W2951102653 @default.
- W2904383797 cites W2953030256 @default.
- W2904383797 cites W2962731536 @default.
- W2904383797 cites W2962760235 @default.
- W2904383797 cites W2962778872 @default.
- W2904383797 cites W2962808998 @default.
- W2904383797 cites W2962849139 @default.
- W2904383797 cites W2962885944 @default.
- W2904383797 cites W2962897886 @default.
- W2904383797 cites W2962988048 @default.
- W2904383797 cites W2963026686 @default.
- W2904383797 cites W2963121255 @default.
- W2904383797 cites W2963245493 @default.
- W2904383797 cites W2963363981 @default.
- W2904383797 cites W2963433432 @default.
- W2904383797 cites W2963547760 @default.
- W2904383797 cites W2963730200 @default.
- W2904383797 cites W2963800363 @default.
- W2904383797 cites W2963850211 @default.
- W2904383797 cites W2963966978 @default.
- W2904383797 cites W2963995996 @default.
- W2904383797 cites W2964137676 @default.
- W2904383797 cites W3102132650 @default.
- W2904383797 hasPublicationYear "2018" @default.
- W2904383797 type Work @default.
- W2904383797 sameAs 2904383797 @default.
- W2904383797 citedByCount "30" @default.
- W2904383797 countsByYear W29043837972019 @default.
- W2904383797 countsByYear W29043837972020 @default.
- W2904383797 countsByYear W29043837972021 @default.