Kunming Luo

Kunming Luo

Auto-generated profile, based on publicly available information

Kunming Luo

Hong Kong University of Science and Technology, Hong Kong, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 July 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
SLShuaicheng Liu
Shuaicheng Liu
KLKunming Luo
Kunming Luo
NYNianjin Ye
Nianjin Ye
CWChuan Wang
Chuan Wang
JWJue Wang
Jue Wang
BZBing Zeng
Bing Zeng
Occlusion is an inevitable and critical problem in unsupervised optical flow learning. Existing methods either treat occlusions equally as non-occluded regions or simply remove them to avoid incorrectness. However, the occlusion regions can provide effective information for optical flow learning. In this paper, we present OIFlow, an occlusion-inpainting framework to make full use of occlusion regions. Specifically, a new appearance-flow network is proposed to inpaint occluded flows based on the image content. Moreover, a boundary dilated warp is proposed to deal with occlusions caused by displacement beyond the image border. We conduct experiments on multiple leading flow benchmark datasets such as Flying Chairs, KITTI and MPI-Sintel, which demonstrate that the performance is significantly improved by our proposed occlusion handling framework.

21 September 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
CWChuan Wang
Chuan Wang
SZShan Zhao
Shan Zhao
LZLi Zhu
Li Zhu
KLKunming Luo
Kunming Luo
YGYanwen Guo
Yanwen Guo
SLShuaicheng Liu
Shuaicheng Liu
In this paper we present a new data-driven method for pixel-level scene text segmentation from a single natural image. Although scene text detection, i.e. producing a text region mask, has been well studied in the past decade, pixel-level text segmentation is still an open problem due to the lack of massive pixel-level labeled data for supervised training. To tackle this issue, we incorporate text region mask as an auxiliary data into this task, considering acquiring large-scale of labeled text region mask is commonly less expensive and time-consuming. To be specific, we propose a mutually guided network which produces a polygon-level mask in one branch and a pixel-level text mask in the other. The two branches’ outputs serve as guidance for each other and the whole network is trained via a semi-supervised learning strategy. Extensive experiments are conducted to demonstrate the effectiveness of our mutually guided network, and experimental results show our network outperforms the state-of-the-art in pixel-level scene text segmentation. We also demonstrate the mask produced by our network could improve the text recognition performance besides the trivial image editing application.

23 November 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
SLShuaicheng Liu
Shuaicheng Liu
KLKunming Luo
Kunming Luo
ALAo Luo
Ao Luo
CWChuan Wang
Chuan Wang
FMFanman Meng
Fanman Meng
BZBing Zeng
Bing Zeng
We present an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network. Specifically, in the pyramid downsampling, we propose a Content-Aware Pooling (CAP) module, which promotes local feature gathering by avoiding cross region pooling, so that the learned features become more representative. In the pyramid upsampling, we propose an Adaptive Flow Upsampling (AFU) module, where cross edge interpolation can be avoided, producing sharp motion boundaries. Equipped with these two modules, our method achieves the best performance for unsupervised optical flow estimation on multiple leading benchmarks, including MPI-Sintel, KITTI 2012 and KITTI 2015. Particularly, we achieve EPE=1.5 on KITTI 2012 and F1=9.67% KITTI 2015, which outperform the previous state-of-the-art methods by 16.7% and 13.1%, respectively.

28 October 2024
Verified
Conference Paper
Open access
HWHongjie Wu
Hongjie Wu
LHLinchao He
Linchao He
MZMingqin Zhang
Mingqin Zhang
DCDongdong Chen
Dongdong Chen
KLKunming Luo
Kunming Luo
JLJiancheng Lv
Jiancheng Lv
Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources.