Search Results for author: Dohae Lee

Found 5 papers, 1 papers with code

Semantic Guidance Tuning for Text-To-Image Diffusion Models

no code implementations26 Dec 2023 Hyun Kang, Dohae Lee, Myungjin Shin, In-Kwon Lee

Based on this observation, we devise a technique to steer the guidance direction towards any concept from which the model diverges.

Zero-shot Generalization

Utilizing Task-Generic Motion Prior to Recover Full-Body Motion from Very Sparse Signals

no code implementations30 Aug 2023 Myungjin Shin, Dohae Lee, In-Kwon Lee

This is based on the premise that the ultimate goal of pose reconstruction is to reconstruct the motion, which is a series of poses.

ClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered Clothes

no code implementations7 Apr 2023 Dohae Lee, Hyun Kang, In-Kwon Lee

We present ClothCombo, a pipeline to drape arbitrary combinations of clothes on 3D human models with varying body shapes and poses.

Garment Reconstruction Virtual Try-on

Flexible Networks for Learning Physical Dynamics of Deformable Objects

1 code implementation7 Dec 2021 Jinhyung Park, Dohae Lee, In-Kwon Lee

This precondition restrains the model from generalizing to real-world data, which is considered to be a sequence of unordered point sets.

Future prediction

Discovering Latent Representations of Relations for Interacting Systems

no code implementations10 Nov 2021 Dohae Lee, Young Jin Oh, In-Kwon Lee

However, existing approaches are difficult to apply if the number of relations is unknown or if the relations are complex.

Decoder Relation

Cannot find the paper you are looking for? You can Submit a new open access paper.