# SkeleGuide: Explicit Skeleton Reasoning for Context-Aware Human-in-Place Image Synthesis Source: [SkeleGuide: Explicit Skeleton Reasoning for Context-Aware Human-in-Place Image Synthesis]() Collection index: [llms.txt]() Data updated: 2026-03-04T05:00:12.635Z Authors: Chuqiao Wu, Jin Song, Yiyun Fei Published: 2026-03-02T08:07:08.000Z ## Abstract Generating realistic and structurally plausible human images into existing scenes remains a significant challenge for current generative models, which often produce artifacts like distorted limbs and unnatural poses. We attribute this systemic failure to an inability to perform explicit reasoning over human skeletal structure. To address this, we introduce SkeleGuide, a novel framework built upon explicit skeletal reasoning. Through joint training of its reasoning and rendering stages, SkeleGuide learns to produce an internal pose that acts as a strong structural prior, guiding the synthesis towards high structural integrity. For fine-grained user control, we introduce PoseInverter, a module that decodes this internal latent pose into an explicit and editable format. Extensive experiments demonstrate that SkeleGuide significantly outperforms both specialized and general-purpose models in generating high-fidelity, contextually-aware human images. Our work provides compelling evidence that explicitly modeling skeletal structure is a fundamental step towards robust and plausible human image synthesis. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Human-in-place Image Synthesis on V-COCO official (test)](): Human-in-place image synthesis; V-COCO official (test); FID: 15.48. ## Original sources and implementation [Original paper]() [PDF]()