Picture for Yifan Xie

Yifan Xie

Universal Visuo-Tactile Video Understanding for Embodied Interaction

Add code
May 28, 2025
Viaarxiv icon

Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration

Add code
May 06, 2025
Figure 1 for Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration
Figure 2 for Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration
Figure 3 for Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration
Figure 4 for Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration
Viaarxiv icon

MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach

Add code
Mar 31, 2025
Figure 1 for MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach
Figure 2 for MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach
Figure 3 for MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach
Figure 4 for MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach
Viaarxiv icon

Object Isolated Attention for Consistent Story Visualization

Add code
Mar 30, 2025
Viaarxiv icon

UniSync: A Unified Framework for Audio-Visual Synchronization

Add code
Mar 20, 2025
Viaarxiv icon

Observation-Graph Interaction and Key-Detail Guidance for Vision and Language Navigation

Add code
Mar 14, 2025
Viaarxiv icon

Unseen Horizons: Unveiling the Real Capability of LLM Code Generation Beyond the Familiar

Add code
Dec 11, 2024
Viaarxiv icon

PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis

Add code
Dec 11, 2024
Figure 1 for PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
Figure 2 for PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
Figure 3 for PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
Figure 4 for PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
Viaarxiv icon

A Review of Human Emotion Synthesis Based on Generative Technology

Add code
Dec 10, 2024
Figure 1 for A Review of Human Emotion Synthesis Based on Generative Technology
Figure 2 for A Review of Human Emotion Synthesis Based on Generative Technology
Figure 3 for A Review of Human Emotion Synthesis Based on Generative Technology
Figure 4 for A Review of Human Emotion Synthesis Based on Generative Technology
Viaarxiv icon

CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis

Add code
Nov 19, 2024
Figure 1 for CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis
Figure 2 for CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis
Figure 3 for CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis
Figure 4 for CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis
Viaarxiv icon