Matches in SemOpenAlex for { <https://semopenalex.org/work/W3013080309> ?p ?o ?g. }
- W3013080309 abstract "In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging domains such as nighttime scenes or adverse weather conditions where assumptions about photometric consistency break down. We propose DeFeat-Net (Depth & Feature network), an approach to simultaneously learn a cross-domain dense feature representation, alongside a robust depth-estimation framework based on warped feature consistency. The resulting feature representation is learned in an unsupervised manner with no explicit ground-truth correspondences required. We show that within a single domain, our technique is comparable to both the current state of the art in monocular depth estimation and supervised feature representation learning. However, by simultaneously learning features, depth and motion, our technique is able to generalize to challenging domains, allowing DeFeat-Net to outperform the current state-of-the-art with around 10% reduction in all error measures on more challenging sequences such as nighttime driving." @default.
- W3013080309 created "2020-04-03" @default.
- W3013080309 creator A5044490167 @default.
- W3013080309 creator A5070969455 @default.
- W3013080309 creator A5091184063 @default.
- W3013080309 date "2020-03-30" @default.
- W3013080309 modified "2023-09-27" @default.
- W3013080309 title "DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning" @default.
- W3013080309 cites W1491719799 @default.
- W3013080309 cites W1532362218 @default.
- W3013080309 cites W1536680647 @default.
- W3013080309 cites W1606951770 @default.
- W3013080309 cites W1677409904 @default.
- W3013080309 cites W1776042733 @default.
- W3013080309 cites W1803059841 @default.
- W3013080309 cites W1881649694 @default.
- W3013080309 cites W1903029394 @default.
- W3013080309 cites W1905829557 @default.
- W3013080309 cites W1979931042 @default.
- W3013080309 cites W1987648924 @default.
- W3013080309 cites W1992178727 @default.
- W3013080309 cites W1997452381 @default.
- W3013080309 cites W2035920683 @default.
- W3013080309 cites W2120657032 @default.
- W3013080309 cites W2125416623 @default.
- W3013080309 cites W2132947399 @default.
- W3013080309 cites W2133665775 @default.
- W3013080309 cites W2141584146 @default.
- W3013080309 cites W2150066425 @default.
- W3013080309 cites W2151103935 @default.
- W3013080309 cites W2171740948 @default.
- W3013080309 cites W2194775991 @default.
- W3013080309 cites W2300779272 @default.
- W3013080309 cites W2320444803 @default.
- W3013080309 cites W2474531669 @default.
- W3013080309 cites W2550031512 @default.
- W3013080309 cites W2558625610 @default.
- W3013080309 cites W2561074213 @default.
- W3013080309 cites W2604231069 @default.
- W3013080309 cites W2608018946 @default.
- W3013080309 cites W2609883120 @default.
- W3013080309 cites W2612112834 @default.
- W3013080309 cites W2740418457 @default.
- W3013080309 cites W2788857104 @default.
- W3013080309 cites W2794337790 @default.
- W3013080309 cites W2794812000 @default.
- W3013080309 cites W2890949887 @default.
- W3013080309 cites W2894983388 @default.
- W3013080309 cites W2901296536 @default.
- W3013080309 cites W2902442348 @default.
- W3013080309 cites W2909119029 @default.
- W3013080309 cites W2913483780 @default.
- W3013080309 cites W2921448249 @default.
- W3013080309 cites W2922389182 @default.
- W3013080309 cites W2932738842 @default.
- W3013080309 cites W2937045595 @default.
- W3013080309 cites W2944011193 @default.
- W3013080309 cites W2948647700 @default.
- W3013080309 cites W2949023359 @default.
- W3013080309 cites W2951524694 @default.
- W3013080309 cites W2962741876 @default.
- W3013080309 cites W2962835968 @default.
- W3013080309 cites W2963231581 @default.
- W3013080309 cites W2963265330 @default.
- W3013080309 cites W2963324085 @default.
- W3013080309 cites W2963412495 @default.
- W3013080309 cites W2963502507 @default.
- W3013080309 cites W2963531306 @default.
- W3013080309 cites W2963537932 @default.
- W3013080309 cites W2963549785 @default.
- W3013080309 cites W2963583471 @default.
- W3013080309 cites W2963591054 @default.
- W3013080309 cites W2963652981 @default.
- W3013080309 cites W2963654727 @default.
- W3013080309 cites W2963906250 @default.
- W3013080309 cites W2964314455 @default.
- W3013080309 cites W2964347182 @default.
- W3013080309 cites W2964968086 @default.
- W3013080309 cites W2975534606 @default.
- W3013080309 cites W3043075211 @default.
- W3013080309 hasPublicationYear "2020" @default.
- W3013080309 type Work @default.
- W3013080309 sameAs 3013080309 @default.
- W3013080309 citedByCount "0" @default.
- W3013080309 crossrefType "posted-content" @default.
- W3013080309 hasAuthorship W3013080309A5044490167 @default.
- W3013080309 hasAuthorship W3013080309A5070969455 @default.
- W3013080309 hasAuthorship W3013080309A5091184063 @default.
- W3013080309 hasConcept C104317684 @default.
- W3013080309 hasConcept C119857082 @default.
- W3013080309 hasConcept C138885662 @default.
- W3013080309 hasConcept C146849305 @default.
- W3013080309 hasConcept C153180895 @default.
- W3013080309 hasConcept C154945302 @default.
- W3013080309 hasConcept C17744445 @default.
- W3013080309 hasConcept C185592680 @default.
- W3013080309 hasConcept C199539241 @default.
- W3013080309 hasConcept C2776359362 @default.
- W3013080309 hasConcept C2776401178 @default.
- W3013080309 hasConcept C2776436953 @default.