6 papers
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
Chanho Park, Daehyeon Choi, Jihyun Lee +1
Vision-language models (VLMs) can locate an image region referred to by a text prompt and route the corresponding visual evidence to the output, yet the internal mechanism behind t…
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Junxuan Li, Rawal Khirodkar, Chengan He +37
High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans wit…
Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
Naru Suzuki, Takehiko Ohkawa, Tatsuro Banno +3
How can we reconstruct 3D hand poses when large portions of the hand are heavily occluded by itself or by objects? Humans often resolve such ambiguities by leveraging contextual kn…
Generative Modeling of Shape-Dependent Self-Contact Human Poses
Takehiko Ohkawa, Jihyun Lee, Shunsuke Saito +7
One can hardly model self-contact of human poses without considering underlying body shapes. For example, the pose of rubbing a belly for a person with a low BMI leads to penetrati…
ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation
Yunhong Min, Daehyeon Choi, Kyeongmin Yeo +2
We introduce ORIGEN, the first zero-shot method for 3D orientation grounding in text-to-image generation across multiple objects and diverse categories. While previous work on spat…
Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics
Woojin Cho, Jihyun Lee, Minjae Yi +8
Existing datasets for 3D hand-object interaction are limited either in the data cardinality, data variations in interaction scenarios, or the quality of annotations. In this work,…