Picture for Song Bai

Song Bai

Alibaba Group, University of Oxford

PVUW 2024 Challenge on Complex Video Understanding: Methods and Results

Add code
Jun 24, 2024
Viaarxiv icon

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

Add code
Jun 07, 2024
Viaarxiv icon

Debiasing Text-to-Image Diffusion Models

Add code
Feb 22, 2024
Figure 1 for Debiasing Text-to-Image Diffusion Models
Figure 2 for Debiasing Text-to-Image Diffusion Models
Figure 3 for Debiasing Text-to-Image Diffusion Models
Figure 4 for Debiasing Text-to-Image Diffusion Models
Viaarxiv icon

Progress and Prospects in 3D Generative AI: A Technical Overview including 3D human

Add code
Jan 05, 2024
Viaarxiv icon

General Object Foundation Model for Images and Videos at Scale

Add code
Dec 14, 2023
Figure 1 for General Object Foundation Model for Images and Videos at Scale
Figure 2 for General Object Foundation Model for Images and Videos at Scale
Figure 3 for General Object Foundation Model for Images and Videos at Scale
Figure 4 for General Object Foundation Model for Images and Videos at Scale
Viaarxiv icon

Learning to Holistically Detect Bridges from Large-Size VHR Remote Sensing Imagery

Add code
Dec 05, 2023
Viaarxiv icon

Dataset Condensation via Generative Model

Add code
Sep 14, 2023
Figure 1 for Dataset Condensation via Generative Model
Figure 2 for Dataset Condensation via Generative Model
Figure 3 for Dataset Condensation via Generative Model
Figure 4 for Dataset Condensation via Generative Model
Viaarxiv icon

Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks

Add code
Aug 13, 2023
Figure 1 for Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks
Figure 2 for Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks
Figure 3 for Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks
Figure 4 for Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks
Viaarxiv icon

Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding

Add code
Aug 01, 2023
Figure 1 for Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
Figure 2 for Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
Figure 3 for Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
Figure 4 for Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
Viaarxiv icon

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

Add code
Jul 09, 2023
Figure 1 for DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
Figure 2 for DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
Figure 3 for DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
Viaarxiv icon