Picture for Xiaoshui Huang

Xiaoshui Huang

PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration

Add code
Jan 14, 2025
Viaarxiv icon

Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation

Add code
Dec 01, 2024
Figure 1 for Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
Figure 2 for Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
Figure 3 for Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
Figure 4 for Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
Viaarxiv icon

An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models

Add code
Nov 25, 2024
Figure 1 for An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
Figure 2 for An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
Figure 3 for An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
Figure 4 for An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
Viaarxiv icon

DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild

Add code
Nov 20, 2024
Figure 1 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Figure 2 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Figure 3 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Figure 4 for DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Viaarxiv icon

DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion

Add code
Oct 31, 2024
Figure 1 for DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Figure 2 for DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Figure 3 for DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Figure 4 for DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Viaarxiv icon

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Add code
Oct 03, 2024
Viaarxiv icon

Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation

Add code
Sep 04, 2024
Figure 1 for Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation
Figure 2 for Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation
Figure 3 for Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation
Figure 4 for Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation
Viaarxiv icon

COMOGen: A Controllable Text-to-3D Multi-object Generation Framework

Add code
Sep 01, 2024
Viaarxiv icon

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

Add code
Jul 13, 2024
Viaarxiv icon

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

Add code
Jun 11, 2024
Figure 1 for Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Figure 2 for Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Figure 3 for Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Figure 4 for Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Viaarxiv icon