activity
20222026
most citedGenerative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning

43 citations · 55 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2026

Struct-GStream: Towards Efficient Free-Viewpoint Video Streaming at Low-Bitrates with Structured 3D Gaussians

Han Jiao, Jiakai Sun, Lei Zhao +4

Constructing photorealistic Free-Viewpoint Videos (FVVs) of dynamic scenes from a set of posed 2D images has been an intriguing yet challenging task in computer vision. Methods bas…

cs.CV2026

RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction

Han Jiao, Chen Liu, Jiakai Sun +6

Large-scale road surface reconstruction supports high-definition mapping, autonomous-driving perception, annotation, and simulation. Existing road-specialized optimization methods…

cs.CV2026

SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentation

Yun Wang, Zhengjie Yang, Jiahao Zheng +3

Recent self-supervised stereo matching methods have made significant progress. They typically rely on the photometric consistency assumption, which presumes corresponding points ac…

cs.CV2026

Fast and Robust Deformable 3D Gaussian Splatting

Han Jiao, Jiakai Sun, Lei Zhao +3

3D Gaussian Splatting has demonstrated remarkable real-time rendering capabilities and superior visual quality in novel view synthesis for static scenes. Building upon these advant…

cs.CV2025

SPAST: Arbitrary Style Transfer with Style Priors via Pre-trained Large-scale Model

Zhanjie Zhang, Quanwei Zhang, Junsheng Luan +3

Given an arbitrary content and style image, arbitrary style transfer aims to render a new stylized image which preserves the content image's structure and possesses the style image…

cs.CV2025

DyArtbank: Diverse Artistic Style Transfer via Pre-trained Stable Diffusion and Dynamic Style Prompt Artbank

Zhanjie Zhang, Quanwei Zhang, Guangyuan Li +4

Artistic style transfer aims to transfer the learned style onto an arbitrary content image. However, most existing style transfer methods can only render consistent artistic styliz…