IEEE Trans Image Process - Toward naturalistic 2D-to-3D conversion.

Tópicos

{ motion(1329) object(1292) video(1091) }
{ imag(1947) propos(1133) code(1026) }
{ state(1844) use(1261) util(961) }
{ problem(2511) optim(1539) algorithm(950) }
{ perform(1367) use(1326) method(1137) }
{ spatial(1525) area(1432) region(1030) }
{ can(774) often(719) complex(702) }
{ system(1976) rule(880) can(841) }
{ estim(2440) model(1874) function(577) }
{ method(1969) cluster(1462) data(1082) }
{ clinic(1479) use(1117) guidelin(835) }
{ data(1714) softwar(1251) tool(1186) }
{ model(2341) predict(2261) use(1141) }
{ design(1359) user(1324) use(1319) }
{ model(2656) set(1616) predict(1553) }
{ age(1611) year(1155) adult(843) }
{ analysi(2126) use(1163) compon(1037) }
{ decis(3086) make(1611) patient(1517) }
{ inform(2794) health(2639) internet(1427) }
{ sequenc(1873) structur(1644) protein(1328) }
{ assess(1506) score(1403) qualiti(1306) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ concept(1167) ontolog(924) domain(897) }
{ extract(1171) text(1153) clinic(932) }
{ control(1307) perform(991) simul(935) }
{ care(1570) inform(1187) nurs(1089) }
{ search(2224) databas(1162) retriev(909) }
{ perform(999) metric(946) measur(919) }
{ system(1050) medic(1026) inform(1018) }
{ visual(1396) interact(850) tool(830) }
{ group(2977) signific(1463) compar(1072) }
{ activ(1138) subject(705) human(624) }
{ use(1733) differ(960) four(931) }
{ drug(1928) target(777) effect(648) }
{ process(1125) use(805) approach(778) }
{ model(3404) distribut(989) bayesian(671) }
{ data(1737) use(1416) pattern(1282) }
{ measur(2081) correl(1212) valu(896) }
{ imag(1057) registr(996) error(939) }
{ bind(1733) structur(1185) ligand(1036) }
{ method(1219) similar(1157) match(930) }
{ featur(3375) classif(2383) classifi(1994) }
{ imag(2830) propos(1344) filter(1198) }
{ network(2748) neural(1063) input(814) }
{ imag(2675) segment(2577) method(1081) }
{ patient(2315) diseas(1263) diabet(1191) }
{ take(945) account(800) differ(722) }
{ studi(2440) review(1878) systemat(933) }
{ framework(1458) process(801) describ(734) }
{ error(1145) method(1030) estim(1020) }
{ chang(1828) time(1643) increas(1301) }
{ learn(2355) train(1041) set(1003) }
{ algorithm(1844) comput(1787) effici(935) }
{ method(1557) propos(1049) approach(1037) }
{ model(2220) cell(1177) simul(1124) }
{ general(901) number(790) one(736) }
{ method(984) reconstruct(947) comput(926) }
{ featur(1941) imag(1645) propos(1176) }
{ case(1353) use(1143) diagnosi(1136) }
{ howev(809) still(633) remain(590) }
{ data(3963) clinic(1234) research(1004) }
{ studi(1410) differ(1259) use(1210) }
{ risk(3053) factor(974) diseas(938) }
{ research(1085) discuss(1038) issu(1018) }
{ import(1318) role(1303) understand(862) }
{ compound(1573) activ(1297) structur(1058) }
{ studi(1119) effect(1106) posit(819) }
{ blood(1257) pressur(1144) flow(957) }
{ record(1888) medic(1808) patient(1693) }
{ health(3367) inform(1360) care(1135) }
{ model(3480) simul(1196) paramet(876) }
{ monitor(1329) mobil(1314) devic(1160) }
{ ehr(2073) health(1662) electron(1139) }
{ research(1218) medic(880) student(794) }
{ patient(2837) hospit(1953) medic(668) }
{ data(2317) use(1299) case(1017) }
{ medic(1828) order(1363) alert(1069) }
{ signal(2180) analysi(812) frequenc(800) }
{ cost(1906) reduc(1198) effect(832) }
{ sampl(1606) size(1419) use(1276) }
{ gene(2352) biolog(1181) express(1162) }
{ data(3008) multipl(1320) sourc(1022) }
{ first(2504) two(1366) second(1323) }
{ intervent(3218) particip(2042) group(1664) }
{ time(1939) patient(1703) rate(768) }
{ patient(1821) servic(1111) care(1106) }
{ use(2086) technolog(871) perceiv(783) }
{ can(981) present(881) function(850) }
{ health(1844) social(1437) communiti(874) }
{ structur(1116) can(940) graph(676) }
{ high(1669) rate(1365) level(1280) }
{ cancer(2502) breast(956) screen(824) }
{ use(976) code(926) identifi(902) }
{ result(1111) use(1088) new(759) }
{ implement(1333) system(1263) develop(1122) }
{ survey(1388) particip(1329) question(1065) }
{ activ(1452) weight(1219) physic(1104) }
{ method(2212) result(1239) propos(1039) }
{ detect(2391) sensit(1101) algorithm(908) }

Resumo

Natural scene statistics (NSSs) models have been developed that make it possible to impose useful perceptually relevant priors on the luminance, colors, and depth maps of natural scenes. We show that these models can be used to develop 3D content creation algorithms that can convert monocular 2D videos into statistically natural 3D-viewable videos. First, accurate depth information on key frames is obtained via human annotation. Then, both forward and backward motion vectors are estimated and compared to decide the initial depth values, and a compensation process is applied to further improve the depth initialization. Then, the luminance/chrominance and initial depth map are decomposed by a Gabor filter bank. Each subband of depth is modeled to produce a NSS prior term. The statistical color-depth priors are combined with the spatial smoothness constraint in the depth propagation target function as a prior regularizing term. The final depth map associated with each frame of the input 2D video is optimized by minimizing the target function over all subbands. In the end, stereoscopic frames are rendered from the color frames and their associated depth maps. We evaluated the quality of the generated 3D videos using both subjective and objective quality assessment methods. The experimental results obtained on various sequences show that the presented method outperforms several state-of-the-art 2D-to-3D conversion methods.

Resumo Limpo

natur scene statist nsss model develop make possibl impos use perceptu relev prior lumin color depth map natur scene show model can use develop d content creation algorithm can convert monocular d video statist natur dviewabl video first accur depth inform key frame obtain via human annot forward backward motion vector estim compar decid initi depth valu compens process appli improv depth initi luminancechromin initi depth map decompos gabor filter bank subband depth model produc nss prior term statist colordepth prior combin spatial smooth constraint depth propag target function prior regular term final depth map associ frame input d video optim minim target function subband end stereoscop frame render color frame associ depth map evalu qualiti generat d video use subject object qualiti assess method experiment result obtain various sequenc show present method outperform sever stateoftheart dtod convers method

Resumos Similares

IEEE Trans Image Process - Toward dynamic image mosaic generation with robustness to parallax. ( 0,814391114430238 )
IEEE Trans Vis Comput Graph - Video-based Crowd Synthesis. ( 0,813797683487558 )
IEEE Trans Image Process - Computational cameras: convergence of optics and processing. ( 0,775554645646926 )
IEEE Trans Image Process - Online object tracking with sparse prototypes. ( 0,759495692289919 )
IEEE Trans Image Process - Video object tracking in the compressed domain using spatio-temporal Markov random fields. ( 0,757388584053449 )
Med Biol Eng Comput - Automatic detection of motion blur in intravital video microscopy image sequences via directional statistics of log-Gabor energy maps. ( 0,753691803065935 )
IEEE Trans Vis Comput Graph - Content-Aware Video Retargeting Using Object-preserving Warping. ( 0,744793210609064 )
IEEE Trans Image Process - Segmentation and tracking multiple objects under occlusion from multiview video. ( 0,743220219129191 )
IEEE Trans Image Process - De-interlacing using nonlocal costs and Markov-chain-based estimation of interpolation methods. ( 0,737741549052758 )
IEEE Trans Image Process - Bidirectional scalable motion for scalable video coding. ( 0,733376762808859 )
Neural Comput - A model of motion transparency processing with local center-surround interactions and feedback. ( 0,723334280901862 )
Int J Med Robot - Hand-eye and radial distortion calibration for rigid endoscopes. ( 0,72209728713645 )
IEEE Trans Vis Comput Graph - Adaptive Motion Data Representation with Repeated Motion Analysis. ( 0,717639784816548 )
IEEE Trans Image Process - Optimal compression plane for efficient video coding. ( 0,717298595963852 )
IEEE Trans Image Process - A novel recursive Bayesian learning-based method for the efficient and accurate segmentation of video with dynamic background. ( 0,710859382445702 )
IEEE Trans Image Process - Maintaining temporal coherence in video retargeting using mosaic-guided scaling. ( 0,707186852428591 )
Int J Comput Assist Radiol Surg - Subject-specific real-time respiratory liver motion compensation method for ultrasound-MRI/CT fusion imaging. ( 0,706769100913254 )
IEEE Trans Image Process - Robust video hashing via multilinear subspace projections. ( 0,704685437831292 )
IEEE Trans Image Process - Patchwise joint sparse tracking with occlusion detection. ( 0,70345075055755 )
IEEE Trans Image Process - Frame-Based Recovery of Corrupted Video Files Using Video Codec Specifications. ( 0,702872949505518 )
Int J Comput Assist Radiol Surg - A robust method to track colonoscopy videos with non-informative images. ( 0,702717096907641 )
IEEE Trans Image Process - JPEG2000-based scalable interactive video (JSIV). ( 0,700899733417609 )
IEEE Trans Image Process - Common and Innovative Visuals: A sparsity modeling framework for video. ( 0,700857591723295 )
IEEE Trans Image Process - Particle filter with a mode tracker for visual tracking across illumination changes. ( 0,697462368643989 )
IEEE Trans Image Process - Exploring visual and motion saliency for automatic video object extraction. ( 0,695291449901073 )
IEEE Trans Vis Comput Graph - Compact Video Synopsis via Global Spatiotemporal Optimization. ( 0,694413992725478 )
IEEE Trans Image Process - Human object inpainting using manifold learning-based posture sequence estimation. ( 0,687017017586446 )
IEEE Trans Image Process - Optimizing the hierarchical prediction and coding in HEVC for surveillance and conference videos with background modeling. ( 0,68648233808638 )
IEEE Trans Image Process - Collaborative sensing in a distributed PTZ camera network. ( 0,685841492799389 )
Comput Math Methods Med - Robust myocardial motion tracking for echocardiography: variational framework integrating local-to-global deformation. ( 0,685691011473414 )
IEEE Trans Image Process - Compressive light field sensing. ( 0,682221028637269 )
IEEE Trans Pattern Anal Mach Intell - A Prism-Mask System for Multispectral Video Acquisition. ( 0,67932757072308 )
Neural Comput - Variation in the local motion statistics of real-life optic flow scenes. ( 0,67692096676011 )
IEEE Trans Pattern Anal Mach Intell - Variational Light Field Analysis for Disparity Estimation and Super-Resolution. ( 0,676749514073276 )
IEEE Trans Pattern Anal Mach Intell - Robust Facial Feature Tracking Using Shape-Constrained Multiresolution-Selected Linear Predictors. ( 0,673038624684382 )
IEEE Trans Image Process - A regularized model-based optimization framework for pan-sharpening. ( 0,672569856550677 )
IEEE Trans Image Process - Locally oriented optical flow computation. ( 0,67246806528183 )
IEEE Trans Image Process - Unequal protection of video data according to slice relevance. ( 0,671986569532244 )
IEEE Trans Image Process - Content-adaptive motion estimation algorithm for coarse-grain SVC. ( 0,670211133722963 )
IEEE Trans Vis Comput Graph - Lighting System for Visual Perception Enhancement in Volume Rendering. ( 0,669107245246332 )
IEEE Trans Image Process - Robust action recognition via borrowing information across video modalities. ( 0,66831730916307 )
IEEE Trans Pattern Anal Mach Intell - Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion. ( 0,667908118964043 )
IEEE Trans Image Process - Occlusion-aware motion layer extraction under large interframe motions. ( 0,667499561422102 )
IEEE Trans Image Process - Video processing for human perceptual visual quality-oriented video coding. ( 0,667450293688179 )
IEEE Trans Pattern Anal Mach Intell - A Geometric Particle Filter for Template-Based Visual Tracking. ( 0,667446753122323 )
IEEE Trans Image Process - Scale Adaptive Dictionary Learning. ( 0,661147365754034 )
IEEE Trans Vis Comput Graph - Robust Relocalization and Its Evaluation For Online Environment Map Construction. ( 0,661016858728145 )
IEEE Trans Image Process - Object tracking via partial least squares analysis. ( 0,658501143285631 )
IEEE Trans Image Process - Feature-specific difference imaging. ( 0,656519320336366 )
Comput Math Methods Med - A biological hierarchical model based underwater moving object detection. ( 0,653972428488477 )
IEEE Trans Image Process - Adaptive online performance evaluation of video trackers. ( 0,65171346875256 )
IEEE Trans Image Process - Variational bayesian super resolution. ( 0,65124588060237 )
IEEE Trans Pattern Anal Mach Intell - Efficient Subframe Video Alignment using Short Descriptors. ( 0,650007606516498 )
IEEE Trans Image Process - Online camera-gyroscope autocalibration for cell phones. ( 0,64856980490652 )
IEEE Trans Image Process - JPEG2000-based scalable interactive video (JSIV) with motion compensation. ( 0,647876229299348 )
IEEE Trans Image Process - Novel true-motion estimation algorithm and its application to motion-compensated temporal frame interpolation. ( 0,646521060162439 )
IEEE Trans Image Process - Video deblurring algorithm using accurate blur kernel estimation and residual deconvolution based on a blurred-unblurred frame pair. ( 0,64504481546258 )
IEEE Trans Image Process - Robust spatiotemporal matching of electronic slides to presentation videos. ( 0,644690612527558 )
IEEE Trans Image Process - Motion estimation without integer-pel search. ( 0,64389854977613 )
IEEE Trans Image Process - Underwater image enhancement by wavelength compensation and dehazing. ( 0,643683263462661 )
IEEE Trans Image Process - Video texture synthesis with multi-frame LBP-TOP and diffeomorphic growth model. ( 0,643564630692966 )
IEEE Trans Pattern Anal Mach Intell - Trajectory Space: A Dual Representation for Nonrigid Structure from Motion. ( 0,642777445522207 )
Int J Comput Assist Radiol Surg - Enhanced visualisation for minimally invasive surgery. ( 0,642609727417388 )
IEEE Trans Image Process - Saliency-aware video compression. ( 0,642061946247556 )
IEEE Trans Image Process - Robust online multiobject tracking with data association and track management. ( 0,640837007550702 )
IEEE Trans Image Process - Re-estimation of motion and reconstruction for distributed video coding. ( 0,640438525327882 )
IEEE Trans Image Process - Virtual mirror rendering with stationary RGB-D cameras and stored 3-D background. ( 0,63999695405095 )
IEEE Trans Image Process - Video alignment for change detection. ( 0,639961150715594 )
IEEE Trans Pattern Anal Mach Intell - Two Cloud-Based Cues for Estimating Scene Structure and Camera Calibration. ( 0,639221457879628 )
IEEE Trans Image Process - Optical flow estimation for flame detection in videos. ( 0,638280550589182 )
IEEE Trans Image Process - Adaptive sensing and optimal power allocation for wireless video sensors with sigma-delta imager. ( 0,637394224207617 )
IEEE Trans Pattern Anal Mach Intell - 3D Traffic Scene Understanding from Movable Platforms. ( 0,637292776807285 )
J Digit Imaging - Performing real-time interactive fiber tracking. ( 0,637280319791242 )
IEEE Trans Image Process - Interactive streaming of stored multiview video using redundant frame structures. ( 0,63527724706552 )
IEEE Trans Image Process - Study of subjective and objective quality assessment of video. ( 0,633159069597174 )
IEEE Trans Pattern Anal Mach Intell - Model-Based 3D Hand Pose Estimation from Monocular Video. ( 0,633118750269032 )
IEEE Trans Image Process - Robust height estimation of moving objects from uncalibrated videos. ( 0,632985287111826 )
IEEE Trans Image Process - Stochastic uncertainty models for the luminance consistency assumption. ( 0,631760071513013 )
IEEE Trans Pattern Anal Mach Intell - Structured Time Series Analysis for Human Action Segmentation and Recognition. ( 0,631052353893821 )
IEEE Trans Image Process - Segmentation and estimation of spatially varying illumination. ( 0,629954896607039 )
IEEE Trans Image Process - Pose estimation with segmentation consistency. ( 0,629091602406451 )
IEEE Trans Pattern Anal Mach Intell - Visual Tracking: An Experimental Survey. ( 0,628936251965162 )
IEEE Trans Pattern Anal Mach Intell - Angular Embedding: A Robust Quadratic Criterion. ( 0,628173207544813 )
IEEE Trans Pattern Anal Mach Intell - Contextualized Trajectory Parsing with Spatio-Temporal Graph. ( 0,627311506416851 )
IEEE Trans Image Process - Camera constraint-free view-based 3-D object retrieval. ( 0,626638837582204 )
IEEE Trans Image Process - Object tracking and target reacquisition based on 3-D range data for moving vehicles. ( 0,626197156107402 )
IEEE Trans Image Process - Multiphase joint segmentation-registration and object tracking for layered images. ( 0,625403844711697 )
IEEE Trans Image Process - Removing motion blur with space-time processing. ( 0,624531069815976 )
IEEE Trans Image Process - A semitransparency-based optical-flow method with a point trajectory model for particle-like video. ( 0,624418299940671 )
IEEE Trans Pattern Anal Mach Intell - Highly Non-Rigid Object Tracking via Patch-based Dynamic Appearance Modeling. ( 0,62411062416148 )
IEEE Trans Image Process - Dealing with parallax in shape-from-focus. ( 0,623611758289253 )
IEEE Trans Pattern Anal Mach Intell - Scene Particles: Unregularized Particle Based Scene Flow Estimation. ( 0,622708565419497 )
IEEE Trans Image Process - Multi-frame super-resolution reconstruction of small moving objects. ( 0,622483000555161 )
IEEE Trans Neural Netw Learn Syst - Asynchronous Event-Based Multikernel Algorithm for High-Speed Visual Features Tracking. ( 0,622477419022344 )
IEEE Trans Vis Comput Graph - 6-DoF Pose Estimation Using a Projected Dense Dot Pattern. ( 0,622256697232483 )
IEEE Trans Image Process - Joint random field model for all-weather moving vehicle detection. ( 0,622101340930445 )
IEEE Trans Image Process - Cluster-based distributed face tracking in camera networks. ( 0,62063185644861 )
Comput Math Methods Med - The research and application of visual saliency and adaptive support vector machine in target tracking field. ( 0,620172851583249 )
IEEE Trans Image Process - Adaptive Kalman filtering for histogram-based appearance learning in infrared imagery. ( 0,620092765956411 )
IEEE Trans Image Process - Temporal frequency of flickering-distortion optimized video halftoning for electronic paper. ( 0,619870515376156 )