FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210880218> ?p ?o ?g. }

• W4210880218 endingPage "161" @default.
• W4210880218 startingPage "148" @default.
• W4210880218 abstract "Single photon avalanche diodes (SPADs) combined with high-frequency time-to-digital converters (TDCs) enable the estimation of photon Time-of-Flight (ToF) for active 3D-depth imaging. Nevertheless, SPAD sensors still face hardware limitations due to a complex pixel readout design and a large amount of data collected by way of pixel-wise histograms. The intrinsic high background illumination (BI) also remains a challenging issue for the related depth reconstruction algorithms. Using a physically-relevant SPAD sensor model, this work tackles these issues by implementing a pixel-wise ToF histogram compressive sensing (CS) with a specific deep generative model based reconstruction. It demonstrates a possible reduction of hardware design constraints while reaching a depth inference root mean square error below 16 centimeters regardless of BI (50–1050 <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$mathrm{W}mathrm{/}{mathrm{2}}^{2}$</tex-math></inline-formula> ) and distance (20 <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$mathrm{m}$</tex-math></inline-formula> ), at a compression ratio (CR) of 10% (32 CS measurements). In addition, this paper introduces a novel multimodal reconstruction from SPAD data, enabling joint depth and luminance estimations. Indeed, since ToF histogram raw data gathers multiple physical scene characteristics, we propose a two-part deep generative model (DGM) capable of inferring Super-Resolved depth maps and normalized luminance images, independently from the average scene BI. Our key contributions related to the DGM topology design are the introduction of proper normalization layers with a learned pile-up effect compensation, multidimensional-multiscale filtering and the concatenation of Softmax-ReLU activation functions to capture both peak-position and relative amplitude features. Numerically, depth and luminance maps reconstructions of natural scenes respectively reach more than 30 dB and 25 dB PSNRs for any CR higher than 2.5%." @default.
• W4210880218 created "2022-02-09" @default.
• W4210880218 creator A5022822165 @default.
• W4210880218 creator A5028308297 @default.
• W4210880218 creator A5070448737 @default.
• W4210880218 creator A5091769660 @default.
• W4210880218 date "2022-01-01" @default.
• W4210880218 modified "2023-09-26" @default.
• W4210880218 title "Luminance-Depth Reconstruction From Compressed Time-of-Flight Histograms" @default.
• W4210880218 cites W125693051 @default.
• W4210880218 cites W1566209738 @default.
• W4210880218 cites W1817699253 @default.
• W4210880218 cites W1852016712 @default.
• W4210880218 cites W1964293644 @default.
• W4210880218 cites W1969575569 @default.
• W4210880218 cites W1983217013 @default.
• W4210880218 cites W1989917143 @default.
• W4210880218 cites W2003258022 @default.
• W4210880218 cites W2012768111 @default.
• W4210880218 cites W2044762091 @default.
• W4210880218 cites W2072479904 @default.
• W4210880218 cites W2086961060 @default.
• W4210880218 cites W2089613850 @default.
• W4210880218 cites W2099395513 @default.
• W4210880218 cites W2100556411 @default.
• W4210880218 cites W2106967375 @default.
• W4210880218 cites W2114904590 @default.
• W4210880218 cites W2119667497 @default.
• W4210880218 cites W2122548617 @default.
• W4210880218 cites W2129173641 @default.
• W4210880218 cites W2129638195 @default.
• W4210880218 cites W2130187411 @default.
• W4210880218 cites W2133255058 @default.
• W4210880218 cites W2153388956 @default.
• W4210880218 cites W2154304330 @default.
• W4210880218 cites W2161265472 @default.
• W4210880218 cites W2292286909 @default.
• W4210880218 cites W2294731987 @default.
• W4210880218 cites W2405052345 @default.
• W4210880218 cites W2411620643 @default.
• W4210880218 cites W2412454633 @default.
• W4210880218 cites W2520322935 @default.
• W4210880218 cites W2545016167 @default.
• W4210880218 cites W2562751859 @default.
• W4210880218 cites W2568283273 @default.
• W4210880218 cites W2574952845 @default.
• W4210880218 cites W2757284236 @default.
• W4210880218 cites W2779877443 @default.
• W4210880218 cites W2781525095 @default.
• W4210880218 cites W2790755095 @default.
• W4210880218 cites W2799176195 @default.
• W4210880218 cites W2799224898 @default.
• W4210880218 cites W2809731038 @default.
• W4210880218 cites W2891282709 @default.
• W4210880218 cites W2898257176 @default.
• W4210880218 cites W2904049309 @default.
• W4210880218 cites W2904965929 @default.
• W4210880218 cites W2906868222 @default.
• W4210880218 cites W2906950685 @default.
• W4210880218 cites W2912672595 @default.
• W4210880218 cites W2943723877 @default.
• W4210880218 cites W2943795341 @default.
• W4210880218 cites W2951697518 @default.
• W4210880218 cites W2953198216 @default.
• W4210880218 cites W2964101377 @default.
• W4210880218 cites W2972777431 @default.
• W4210880218 cites W2977164968 @default.
• W4210880218 cites W2981207505 @default.
• W4210880218 cites W2991860863 @default.
• W4210880218 cites W2995558547 @default.
• W4210880218 cites W3005645208 @default.
• W4210880218 cites W3005771825 @default.
• W4210880218 cites W3007587201 @default.
• W4210880218 cites W3011749650 @default.
• W4210880218 cites W3013529009 @default.
• W4210880218 cites W3018664053 @default.
• W4210880218 cites W3039585879 @default.
• W4210880218 cites W3086903172 @default.
• W4210880218 cites W3100158650 @default.
• W4210880218 cites W3102722370 @default.
• W4210880218 cites W3102929960 @default.
• W4210880218 cites W3103921058 @default.
• W4210880218 cites W3104915294 @default.
• W4210880218 cites W3104943473 @default.
• W4210880218 cites W3124881766 @default.
• W4210880218 cites W3125735862 @default.
• W4210880218 cites W3128112652 @default.
• W4210880218 cites W3135540272 @default.
• W4210880218 cites W3200746860 @default.
• W4210880218 cites W4250955649 @default.
• W4210880218 cites W2801417207 @default.
• W4210880218 doi "https://doi.org/10.1109/tci.2022.3149088" @default.
• W4210880218 hasPublicationYear "2022" @default.
• W4210880218 type Work @default.
• W4210880218 citedByCount "3" @default.
• W4210880218 countsByYear W42108802182022 @default.
• W4210880218 countsByYear W42108802182023 @default.
• W4210880218 crossrefType "journal-article" @default.

• next