Visual Fidelity

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 43% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 82

All topics

SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection
May 17, 2026Zixi Wei, Huixuaun Zhang, Xiaojun WanAi-Generated Video Detection Generative Video Models
Wangxuan Institute of Computer Technology, Peking University
MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation
May 16, 2026Shuowei Li, Yuming Zhao, Parth Bhalerao +1Text-To-Video Generation Model Visual Fidelity
Santa Clara University, Santa Clara, USA
MechVerse: Evaluating Physical Motion Consistency in Video Generation Models
May 14, 2026Rahul Jain, Mayank Patel, Asim Unmesh +1Video Generation Kinematics
School of Electrical and Computer Engineering, Purdue University · School of Mechanical Engineering, Purdue University
NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics
May 8, 2026Jian Lan, Zhicheng Liu, Xinpeng Wang +5Ava-Vlm Stable Spatial Understanding
University of Munich (LMU), Germany 2Munich Center of Machine Learning3 Sichuan University
LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
May 8, 2026Haewon Jeon, Si-Hyeon LeeDiffusion Models Diffusion Sampling
School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon, South Korea
RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
May 7, 2026Youcan Xu, Jiaxin Shi, Zhen Wang +5Autoregressive Video Generation Real-Time Systems
Zhejiang University, China · Xmax.AI Ltd., China · Hong Kong University of Science and Technology, China
Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models
May 6, 2026Huatian Zhang, Zhendong Mao, Lei Zhang +1Large Language Model Uncertainty Multimodal Large Language Models
University of Science and Technology of China
A Hybrid Approach for Closing the Sim2real Appearance Gap in Game Engine Synthetic Datasets
May 4, 2026Stefanos PasiosSynthetic-To-Real Domain Gap Sim-To-Real Gap
independent researcher
Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration
May 1, 2026Zhili Li, Kangyang Chai, Zhihao Wang +6Hyperspectral Image Super-Resolution Remote Sensing
University of Maryland · University of Pittsburgh · Worcester Polytechnic Institute +1
AesRM: Improving Video Aesthetics with Expert-Level Feedback
Apr 30, 2026Yujin Han, Yujie Wei, Yefei He +7Aesthetics Generative Video Models
The University of Hong Kong · Alibaba Group · Fudan University +3
Breaking Watermarks in the Frequency Domain: A Modulated Diffusion Attack Framework
Apr 24, 2026Chunpeng Wang, Binyan Qu, Xiaoyu Wang +4Watermarks Diffusion Models
Qilu University of Technology (Shandong Academy of Sciences) Jinan, Shandong Province, China · Dalian Maritime University Dalian, Liaoning Province, China · Nanjing University of Science and Technology Nanjing, Jiangsu Province, China +1
Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models
Apr 23, 2026Mohammed Safi Ur Rahman Khan, Sanjay Suryanarayanan, Tushar Anand +1Large Language Model Evaluation Blind Spots
♠Nilekani Centre at AI4Bharat ♢Indian Institute of Technology Madras · ♠Nilekani Centre at AI4Bharat · ♣BITS Pilani, Hyderabad
Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
Apr 22, 2026Diandian Gu, Jing Lin, Gaohong Liu +25High-Fidelity 3D Generation 3D Generation
ByteDance Seed
Evian: Towards Explainable Visual Instruction-tuning Data Auditing
Apr 22, 2026Zimu Jia, Mingjie Xu, Andrew Estornell +1Recent Vision-Language Models Data Quality
1The Hong Kong University of Science and Technology (Guangzhou) · 2ByteDance Seed
FlowC2S: Flowing from Current to Succeeding Frames for Fast and Memory-Efficient Video Continuation
Apr 19, 2026Hovhannes Margaryan, Quentin Bammey, Christian SandorContinuation Visual Fidelity
Team ARAI, Universit´e Paris-Saclay, CNRS, LISN, France · LTCI, T´el´ecom Paris, Institut Polytechnique de Paris, France
More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage
Apr 19, 2026Wei HeWeak Visual Grounding Semantic Gap
IDSAI, University of Exeter Exeter, UK
Splats in Splats++: Robust and Generalizable 3D Gaussian Splatting Steganography
Apr 17, 2026Yijia Guo, Wenkai Huang, Tong Hu +9Steganography 3D Generation
State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, 100871, China · Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China · National Biomedical Imaging Center, College of Future Technology, Peking University, Beijing, 100871, China +2
Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
Apr 16, 2026Yixuan Ding, Wei Huang, Ruijie Quan +2Image Editing Edit
Zhejiang University · The University of Hong Kong
Cross-Resolution Distribution Matching for Diffusion Distillation
Mar 6, 2026Feiyang Chen, Hongpeng Pan, Haonan Xu +3Visual Fidelity Distributions
Huawei, Shanghai & Hangzhou, China · Nanjing University of Science and Technology, Nanjing, China
When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators
Feb 23, 2026Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov +3Modern Text-To-Image Models Synthetic Training Data
1RPTU University Kaiserslautern-Landau, Kaiserslautern, Germany · 2German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding
Nov 25, 2025Haoze Zhang, Tianyu Huang, Zichen Wan +4Generative Video Models Video Generation
1Harbin Institute of Technology, China
SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
Nov 12, 2025Tairan Huang, Yulin Jin, Junxu Liu +2Black-Box Adversarial Attacks Offline Reinforcement Learning
The Hong Kong Polytechnic University Hong Kong, China

May 17, 2026, cs.CVJ/K move · Enter open · S save

SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection

Zixi Wei, Huixuaun Zhang, Xiaojun Wan

Wangxuan Institute of Computer Technology, Peking University

Ai-Generated Video Detection Generative Video Models Visual Fidelity Generative Models Spectral

Open paper AskPDF arXiv

The remarkable visual fidelity of recent commercial video generative models, such as Sora and Veo, renders robust AI-generated video detection increasingly essential to prevent synthetic content from being indistinguishable from real videos and exploited for disinformation. However, existing detectors often fail due to an over-reliance on increasingly realistic semantic features, neglecting subtle spectral artifacts. In this paper, we propose SpecSem-Net, the first framework to introduce a semantic-guided spectral denoising mechanism specifically for high-fidelity AI-generated video detection. Specifically, we design a spectral module to extract high-frequency features via Fourier-Transform based filtering. Furthermore, to reduce misjudgments arising from spectral noise, we employ a Gated Merging Mechanism to adaptively fuse semantic context, effectively mitigating spectral noise. Additionally, to evaluate detector performance on the latest top-tier generative models, we construct a comprehensive benchmark comprising 5 SOTA commercial generators. Extensive experiments demonstrate that SpecSem-Net outperforms existing methods, achieving accuracies of 87.25% and 95.59% on our benchmark and public datasets, respectively.

Momentum

Related topics

Latest papers 82