paper

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

paperactiveprovisionalpose-icl-3d-aware-in-context-learning-for-pose-controllable-subject-customization-acd70fee·1 events·first seen 7d ago

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 In-Context Multiple Instance Learning Observe-and-Act Adaptive Context Selection Contrastive Language-Image Pretraining (CLIP)In-Context Reward Adaptation Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies Preserving Plasticity in Continual Learning via Dynamical Isometry in-context learning Subject-driven Image Generation Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions

Recent events (1)

4arXiv · cs.AI·7d ago·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