Jun Hao Liew

papers

925

total citations

papers (15)

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

CVPR 2024arXiv

327

citations

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

CVPR 2024arXiv

314

citations

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

NEURIPS 2023arXiv

citations

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

ICCV 2025arXiv

citations

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

ICCV 2025arXiv

citations

XAGen: 3D Expressive Human Avatars Generation

NEURIPS 2023arXiv

citations

MagicArticulate: Make Your 3D Models Articulation-Ready

CVPR 2025arXiv

citations

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

NEURIPS 2023

citations

Slim Scissors: Segmenting Thin Object from Synthetic Background

ECCV 2022

citations

Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation Costs

CVPR 2021

citations

Interactive Object Segmentation With Inside-Outside Guidance

CVPR 2020

citations

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

ICCV 2025

citations

Jun Hao Liew

papers (15)

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

Body Meshes as Points

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

XAGen: 3D Expressive Human Avatars Generation

MagicArticulate: Make Your 3D Models Articulation-Ready

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

Slim Scissors: Segmenting Thin Object from Synthetic Background

Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation Costs

Interactive Object Segmentation With Inside-Outside Guidance

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

papers (15)

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

Body Meshes as Points

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

XAGen: 3D Expressive Human Avatars Generation

MagicArticulate: Make Your 3D Models Articulation-Ready

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

Slim Scissors: Segmenting Thin Object from Synthetic Background

Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation Costs

Interactive Object Segmentation With Inside-Outside Guidance

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing