Over the last decade, parallel advances in an area of computer
vision research called ‘structure from motion’ (SfM) has been
driven by a different rationale e to enable automated model production
from unconstrained imagery, for which metric accuracy is
not the primary goal. Some of the most significant advances in SfM
have arisen from the development of image feature descriptors that
are tolerant to changes in view point (e.g., Lowe, 2004), and robust
matching algorithms that can identify and reject errors when they
occur (e.g., Fischler and Bolles, 1981).
Over the last decade, parallel advances in an area of computervision research called ‘structure from motion’ (SfM) has beendriven by a different rationale e to enable automated model productionfrom unconstrained imagery, for which metric accuracy isnot the primary goal. Some of the most significant advances in SfMhave arisen from the development of image feature descriptors thatare tolerant to changes in view point (e.g., Lowe, 2004), and robustmatching algorithms that can identify and reject errors when theyoccur (e.g., Fischler and Bolles, 1981).
การแปล กรุณารอสักครู่..
