SkeleGuide: Explicit Skeleton Reasoning for Context-Aware Human-in-Place Image Synthesis
This addresses the challenge of plausible human image synthesis for applications in graphics and AI, representing an incremental improvement with a novel method.
The paper tackled the problem of generating realistic human images in existing scenes by introducing SkeleGuide, a framework that uses explicit skeletal reasoning to reduce artifacts like distorted limbs, resulting in significantly outperforming other models in high-fidelity synthesis.
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.