» Authors » Lizhuang Ma

Lizhuang Ma

Explore the profile of Lizhuang Ma including associated specialties, affiliations and a list of published articles. Areas
Snapshot
Articles 29
Citations 88
Followers 0
Related Specialties
Top 10 Co-Authors
Published In
Affiliations
Soon will be listed here.
Recent Articles
1.
Qiao J, Lin S, Zhang Y, Li W, Hu J, He G, et al.
Neural Netw . 2025 Jan; 184:107119. PMID: 39798352
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution...
2.
Xie Z, Qiu R, Wang S, Tan X, Xie Y, Ma L
IEEE Trans Image Process . 2024 Jun; 33:3921-3934. PMID: 38913509
Night-time scene parsing aims to extract pixel-level semantic information in night images, aiding downstream tasks in understanding scene object distribution. Due to limited labeled night image datasets, unsupervised domain adaptation...
3.
Liu F, Gong J, Zhou Q, Lu X, Yi R, Xie Y, et al.
IEEE Trans Vis Comput Graph . 2024 Apr; 31(4):2182-2195. PMID: 38557621
Due to the unsatisfactory performance of supervised methods on unpaired real-world scans, point cloud completion via cross-domain adaptation has recently drawn growing attention. Nevertheless, previous approaches only focus on alleviating...
4.
Tian X, Zhang Z, Wang C, Zhang W, Qu Y, Ma L, et al.
IEEE Trans Pattern Anal Mach Intell . 2023 Dec; 46(7):4551-4566. PMID: 38133979
Information Bottleneck (IB) provides an information-theoretic principle for multi-view learning by revealing the various components contained in each viewpoint. This highlights the necessity to capture their distinct roles to achieve...
5.
Tang J, Zhang B, Yang B, Zhang T, Chen D, Ma L, et al.
IEEE Trans Vis Comput Graph . 2023 Oct; 30(9):6020-6037. PMID: 37847635
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative...
6.
Tan X, Ma Q, Gong J, Xu J, Zhang Z, Song H, et al.
IEEE Trans Pattern Anal Mach Intell . 2023 Sep; 45(12):15328-15344. PMID: 37751346
Hidden features in the neural networks usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved by omni-scale...
7.
Xie Z, Wang S, Xu K, Zhang Z, Tan X, Xie Y, et al.
IEEE Trans Image Process . 2023 Apr; 32:2386-2398. PMID: 37071518
Night-Time Scene Parsing (NTSP) is essential to many vision applications, especially for autonomous driving. Most of the existing methods are proposed for day-time scene parsing. They rely on modeling pixel...
8.
Zhou Q, Gu Q, Pang J, Lu X, Ma L
IEEE Trans Pattern Anal Mach Intell . 2023 Apr; 45(7):8954-8968. PMID: 37022055
Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically...
9.
Wang N, Lin S, Li X, Li K, Shen Y, Gao Y, et al.
IEEE Trans Med Imaging . 2023 Apr; 42(9):2740-2750. PMID: 37018113
U-Nets have achieved tremendous success in medical image segmentation. Nevertheless, it may have limitations in global (long-range) contextual interactions and edge-detail preservation. In contrast, the Transformer module has an excellent...
10.
Zhou Q, Li X, He L, Yang Y, Cheng G, Tong Y, et al.
IEEE Trans Pattern Anal Mach Intell . 2022 Nov; 45(6):7853-7869. PMID: 36417746
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However,...