2 citations · 4 across the 16 of their papers we have counts for
23 papers
FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection
Leqi Zhu, Junyan Ye, Kaiqing Lin +3
The development of generative artificial intelligence technologies has propelled the visual realism of synthetic images to an unprecedented level. Although current interpretable de…
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
Junyan Ye, Leiqi Zhu, Yuncheng Guo +7
With the continuous advancement of image generation technology, advanced models such as GPT-Image-1 and Qwen-Image have achieved remarkable text-to-image consistency and world know…
OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild
Yuncheng Guo, Junyan Ye, Chenjue Zhang +4
A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, en…
BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
Junyan Ye, Dongzhi Jiang, Jun He +6
Recently, Multimodal Large Language Models (MLLMs) have made rapid progress, particularly in enhancing their reasoning capabilities. However, existing reasoning benchmarks still pr…
Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents
Peilin Feng, Zhutao Lv, Junyan Ye +8
Earth observation (EO) is essential for understanding the evolving states of the Earth system. Although recent MLLMs have advanced EO research, they still lack the capability to ta…
Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation
Junyan Ye, Dongzhi Jiang, Zihao Wang +9
Recently, GPT-4o has garnered significant attention for its strong performance in image generation, yet open-source models still lag behind. Several studies have explored distillin…
GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation
Zhiyuan Yan, Junyan Ye, Weijia Li +7
The recent breakthroughs in OpenAI's GPT4o model have demonstrated surprisingly good capabilities in image generation and editing, resulting in significant excitement in the commun…
LEGION: Learning to Ground and Explain for Synthetic Image Detection
Hengrui Kang, Siwei Wen, Zichen Wen +8
The rapid advancements in generative technology have emerged as a double-edged sword. While offering powerful tools that enhance convenience, they also pose significant social conc…
Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
Siwei Wen, Junyan Ye, Peilin Feng +7
With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challe…
Where am I? Cross-View Geo-localization with Natural Language Descriptions
Junyan Ye, Honglin Lin, Leyan Ou +5
Cross-view geo-localization identifies the locations of street-view images by matching them with geo-tagged satellite images or OSM. However, most existing studies focus on image-t…
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
Junyan Ye, Baichuan Zhou, Zilong Huang +12
With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data in…
Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning
Weijia Li, Jinhua Yu, Dairong Chen +5
In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enh…
CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis
Weijia Li, Jun He, Junyan Ye +5
Satellite-to-street view synthesis aims at generating a realistic street-view image from its corresponding satellite-view image. Although stable diffusion models have exhibit remar…
Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network
Junyan Ye, Zhutao Lv, Weijia Li +4
Cross-view geolocalization identifies the geographic location of street view images by matching them with a georeferenced satellite database. Significant challenges arise due to th…
UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios
Baichuan Zhou, Haote Yang, Dairong Chen +7
Recent evaluations of Large Multimodal Models (LMMs) have explored their capabilities in various domains, with only few benchmarks specifically focusing on urban environments. More…
Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis
Junyan Ye, Jun He, Weijia Li +5
Ground-to-aerial image synthesis focuses on generating realistic aerial images from corresponding ground street view images while maintaining consistent content layout, simulating…
SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models
Zheng Liu, Hao Liang, Bozhou Li +5
Vision-Language Models (VLMs) have recently emerged, demonstrating remarkable vision-understanding capabilities. However, training these models requires large-scale datasets, which…
3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions
Weijia Li, Haote Yang, Zhenghao Hu +3
3D building reconstruction from monocular remote sensing images is an important and challenging research problem that has received increasing attention in recent years, owing to it…
SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation
Junyan Ye, Qiyan Luo, Jinhua Yu +4
This paper aims at achieving fine-grained building attribute segmentation in a cross-view scenario, i.e., using satellite and street-view image pairs. The main challenge lies in ov…
Parrot Captions Teach CLIP to Spot Text
Yiqi Lin, Conghui He, Alex Jinpeng Wang +3
Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to `Parrot' the vi…
OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images
Weijia Li, Yawen Lai, Linning Xu +5
This paper presents OmniCity, a new dataset for omnipotent city understanding from multi-level and multi-view images. More precisely, the OmniCity contains multi-view satellite ima…
Exploring the Interactive Guidance for Unified and Effective Image Matting
Dinghao Yang, Bin Wang, Weijia Li +2
Recent image matting studies are developing towards proposing trimap-free or interactive methods for complete complex image matting tasks. Although avoiding the extensive labors of…
Influence Selection for Active Learning
Zhuoming Liu, Hao Ding, Huaping Zhong +3
The existing active learning methods select the samples by evaluating the sample's uncertainty or its effect on the diversity of labeled datasets based on different task-specific o…