technique

Surface-Anchored Position Embedding

techniqueactiveprovisionalsurface-anchored-position-embedding-d07607ea·1 events·first seen 7d ago

Aliases: Surface-Anchored Position Embedding

Co-occurring entities

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

More like this (12)

Rotary Position Embedding (RoPE)static embeddings Positional Encoding LCO-Embedding Instructional Segment Embeddings embedding models Hugging Face Embedding Container Joint Embedding Predictive Architecture (JEPA)text-embedding-ada-002 ParaEmbed 2.0 instruction embedding models Latent-Anchored GRPO

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