Ke Fan

papers

168

total citations

papers (11)

FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis

ECCV 2024arXiv

citations

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

ICCV 2025arXiv

citations

Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

CVPR 2025arXiv

citations

TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation

CVPR 2025arXiv

citations

Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation

ICCV 2023arXiv

citations

Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text

CVPR 2024arXiv

citations

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

CVPR 2024arXiv

citations

Test-Time Linear Out-of-Distribution Detection

CVPR 2024

citations

Ke Fan

papers (11)

FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

Adaptive Slot Attention: Object Discovery with Dynamic Slot Number

Unsupervised Open-Vocabulary Object Localization in Videos

Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation

Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation

Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

Test-Time Linear Out-of-Distribution Detection

papers (11)

FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

Adaptive Slot Attention: Object Discovery with Dynamic Slot Number

Unsupervised Open-Vocabulary Object Localization in Videos

Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation

Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation

Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

Test-Time Linear Out-of-Distribution Detection