@article{sun_wu_2022, title={Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis}, volume={44}, ISSN={["1939-3539"]}, DOI={10.1109/TPAMI.2021.3078577}, abstractNote={With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable structured inputs. This paper focuses on a recently emerged task, layout-to-image, whose goal is to learn generative models for synthesizing photo-realistic images from a spatial layout (i.e., object bounding boxes configured in an image lattice) and its style codes (i.e., structural and appearance variations encoded by latent vectors). This paper first proposes an intuitive paradigm for the task, layout-to-mask-to-image, which learns to unfold object masks in a weakly-supervised way based on an input layout and object style codes. The layout-to-mask component deeply interacts with layers in the generator network to bridge the gap between an input layout and synthesized images. Then, this paper presents a method built on Generative Adversarial Networks (GANs) for the proposed layout-to-mask-to-image synthesis with layout and style control at both image and object levels. The controllability is realized by a proposed novel Instance-Sensitive and Layout-Aware Normalization (ISLA-Norm) scheme. A layout semi-supervised version of the proposed method is further developed without sacrificing performance. In experiments, the proposed method is tested in the COCO-Stuff dataset and the Visual Genome dataset with state-of-the-art performance obtained.}, number={9}, journal={IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE}, author={Sun, Wei and Wu, Tianfu}, year={2022}, month={Jan}, pages={5070–5087} }
 @article{teng_sun_liu_yang_lau_2019, title={Mobility-Aware Transmit Beamforming for Ultra-Dense Networks With Sparse Feedback}, volume={68}, ISSN={["1939-9359"]}, DOI={10.1109/TVT.2018.2886800}, abstractNote={The network densification brings favored channel gain. However, its performance is limited by the increased interference and feedback overhead. In this paper, we focus on the channel state information (CSI) measure error induced by feedback delay and study the effect of the uplink feedback on the downlink transmission performance in ultra-dense networks (UDNs). Using a mobility-aware sparse feedback scheme (MSFS), we analyze the feedback transmission delay and feedback waiting delay separately, considering the impact of CSI feedback probability and measurement range. To capture the effect of proposed MSFS, the coverage probability for a typical mobile user is derived, where the imperfect-CSI-based zero-forcing precoding is employed to mitigate the severe inter-cell interference in UDNs. Numerical results reveal that MSFS succeeds in providing the effective CSI for downlink precoding while keeping a lower feedback load, and the optimal feedback probability and measurement range are provided for diverse mobility cases and different network densities.}, number={2}, journal={IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY}, author={Teng, Yinglei and Sun, Weiqi and Liu, An and Yang, Ruizhe and Lau, Vincent K. N.}, year={2019}, month={Feb}, pages={1968–1972} }