Entity · paper

Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization

paperactivepose-icl-3d-aware-in-context-learning-for-pose-controllable-subject-customization-acd70fee·1 events·first seen Jun 10, 2026

Aliases: Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization

Co-occurring entities

Surface-Anchored Position Embedding Pose-ICL

More like this (12)

Pose-ICL Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction Learning Action Priors for Cross-embodiment Robot Manipulation In-Context Multiple Instance Learning Masked Image Modeling Multi-Task Bayesian In-Context Learning Observe-and-Act Adaptive Context Selection Cost-Sensitive Conformal Prediction and Human-in-the-Loop Abstention for Imbalanced High-Stakes Decision Support: A Multi-Domain Benchmark Concept-Constrained Prompt Learning ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation Contrastive Language-Image Pretraining (CLIP)Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications

Recent events (1)

4arXiv · cs.AI·Jun 10, 2026·source ↗

Pose-ICL: 3D-aware in-context learning for pose-controllable image generation of custom subjects

Researchers introduce Pose-ICL, a tuning-free framework for generating images of user-specified subjects with accurate pose control. The method uses Surface-Anchored Position Embedding (SAPE) to give 2D diffusion models explicit 3D awareness by anchoring image tokens to volumetric bounding box surface coordinates. Evaluations on 3D assets and real-world subjects show improvements over existing methods in both pose accuracy and identity consistency. The framework is designed for compatibility with existing Diffusion Transformer (DiT) models.

Multimodal Progress Surface-Anchored Position Embedding Pose-ICL Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization