collaborators

6 papers

cs.CV2025

D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal

Linhao Li, Boya Jin, Zizhe Li +4

Shadow removal aims to restore images that are partially degraded by shadows, where the degradation is spatially localized and non-uniform. Unlike general restoration tasks that as…

cs.CV2025

Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors

Lanqing Guo, Yufei Wang, Hezhen Hu +4

Many 3D scene editing tasks focus on modifying local regions rather than the entire scene, except for some global applications like style transfer, and in the context of 3D Gaussia…

cs.CV2025

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

Shuo Xing, Lanqing Guo, Hongyuan Hua +5

Recent Multimodal Large Language Models (MLLMs) excel on benchmark vision-language tasks, yet little is known about how input visual quality shapes their responses. Does higher per…

cs.CV2025

Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait

Feng Liu, Nicholas Chimitt, Lanqing Guo +16

We address the problem of whole-body person recognition in unconstrained environments. This problem arises in surveillance scenarios such as those in the IARPA Biometric Recognitio…

cs.CV2024

Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method

Yan Zheng, Zhenxiao Liang, Xiaoyan Cong +4

We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-poin…

cs.CV2024

HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts

Xinyu Liu, Yingqing He, Lanqing Guo +10

The potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural a…