outskirts
发表于 2025-3-28 15:56:49
Snap Angle Prediction for 360, Panoramasage may enable content-aware projection with fewer perceptible distortions. Whereas existing approaches assume the viewpoint is fixed, intuitively some viewing angles within the sphere preserve high-level objects better than others. To discover the relationship between these optimal . and the spheri
crescendo
发表于 2025-3-28 20:08:02
http://reply.papertrans.cn/24/2342/234194/234194_42.png
commune
发表于 2025-3-28 23:38:52
DF-Net: Unsupervised Joint Learning of Depth and Flow Using Cross-Task Consistencyled video sequences. Existing unsupervised methods often exploit brightness constancy and spatial smoothness priors to train depth or flow models. In this paper, we propose to leverage geometric consistency as additional supervisory signals. Our core idea is that for rigid regions we can use the pre
懒惰民族
发表于 2025-3-29 04:33:04
http://reply.papertrans.cn/24/2342/234194/234194_44.png
Rejuvenate
发表于 2025-3-29 09:59:59
Transductive Centroid Projection for Semi-supervised Large-Scale Recognitiononal complexity when collaborating with Convolutional Neural Networks. To this end, we design a simple but effective learning mechanism that merely substitutes the last fully-connected layer with the proposed Transductive Centroid Projection (TCP) module. It is inspired by the observation of the wei
怪物
发表于 2025-3-29 14:49:52
http://reply.papertrans.cn/24/2342/234194/234194_46.png
FECT
发表于 2025-3-29 17:45:10
Into the Twilight Zone: Depth Estimation Using Joint Structure-Stereo Optimizationenoising approach – which we show to be ineffective for stereo due to its artefacts and the questionable use of the PSNR metric, we propose to instead rely on structures comprising of piecewise constant regions and principal edges in the given image, as these are the important regions for extracting
灌输
发表于 2025-3-29 21:26:44
Recycle-GAN: Unsupervised Video Retargetingative to a domain, i.e., if contents of John Oliver’s speech were to be transferred to Stephen Colbert, then the generated content/speech should be in Stephen Colbert’s style. Our approach combines both spatial and temporal information along with adversarial losses for content translation and style
Crepitus
发表于 2025-3-30 02:46:44
http://reply.papertrans.cn/24/2342/234194/234194_49.png
香料
发表于 2025-3-30 06:23:56
Open Set Domain Adaptation by Backpropagatione proposed for closed-set scenario, where the source and the target domain completely share the class of their samples. However, in practice, a target domain can contain samples of classes that are not shared by the source domain. We call such classes the “unknown class” and algorithms that work wel