Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body
Zeqing Wang, Qingyang Ma, Wentao Wan, Haojie Li, Keze Wang, Yonghong Tian
Abstract
Recent improvements in visual synthesis have significantly enhanced the depiction of generated human photos, which are pivotal due to their wide applicability and demand. Nonetheless, the existing text-to-image or text-to-video models often generate low-quality human photos that might differ considerably from real-world body structures, referred to as "abnormal human bodies". Such abnormalities, typically deemed unacceptable, pose considerable challenges in the detection and repair of them within human photos. These challenges require precise abnormality recognition capabilities, which entail pinpointing both the location and the abnormality type. Intuitively, Visual Language Models (VLMs) that have obtained remarkable performance on various visual tasks are quite suitable for this task. However, their performance on abnormality detection in human photos is quite poor.Hence, it is quite important to highlight this task for the research community. In this paper, we first introduce a simple yet challenging task, i.e., Fine-grained Human-body Abnormality Detection (FHAD), and construct two high-quality datasets for evaluation. Then, we propose a meticulous framework, named HumanCalibrator, which identifies and repairs abnormalities in human body structures while preserving the other content. Experiments indicate that our HumanCalibrator achieves high accuracy in abnormality detection and accomplishes an increase in visual comparisons while preserving the other visual content.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Agentic Retoucher for Text-To-Image Generation cites High-Resolution Image Synthesis with Latent Diffusion Models
- Agentic Retoucher for Text-To-Image Generation cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Agentic Retoucher for Text-To-Image Generation cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
- GenShield: Unified Detection and Artifact Correction for AI-Generated Images cites High-Resolution Image Synthesis with Latent Diffusion Models
- GenShield: Unified Detection and Artifact Correction for AI-Generated Images cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- GenShield: Unified Detection and Artifact Correction for AI-Generated Images cites Learning Transferable Visual Models From Natural Language Supervision
- Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection cites High-Resolution Image Synthesis with Latent Diffusion Models
- Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- Learning Transferable Visual Models From Natural Language Supervision cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Learning Transferable Visual Models From Natural Language Supervision
Cited by top-tier papers3
- Agentic Retoucher for Text-To-Image GenerationShaocheng Shen, Jianfeng Liang, Chunlei Cai, Cong Geng et al.CVPR 2026 · 9 citations
- Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image DetectionYao Xiao, Weiyan Chen, Jiahao Chen, Zijie Cao et al.ICLR 2026 · 4 citations
- GenShield: Unified Detection and Artifact Correction for AI-Generated ImagesZhipei Xu, Xuanyu Zhang, Youmin Xu, Qing Huang et al.ICML 2026 · 1 citation
Builds on36
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 7,873 citations
Related papers
- ZINA: Multimodal Fine-grained Hallucination Detection and EditingYuiga Wada, Kazuki Matsuda, Komei Sugiura, Graham NeubigCVPR 2026 · 5 citations
- Detecting Violations of Physical Common Sense in Images: A Challenge Dataset and Effective ModelWeibin Wu, Zitong Wang, Zhengjie Luo, Wenqing Chen et al.ACM MM 2025
- Symbal: Detecting Systematic Misalignments in Model-Generated CaptionsMaya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari et al.ICML 2026
- InteractVLM: 3D Interaction Reasoning from 2D Foundational ModelsSai Kumar Dwivedi, Dimitrije Antic, Shashank Tripathi, Omid Taheri et al.CVPR 2025
- MHALO: Evaluating MLLMs as Fine-grained Hallucination DetectorsYishuo Cai, Renjie Gu, Jiaxu Li, Xuancheng Huang et al.ACL Findings 2025
