Jianan Wang

17

Papers

241

Total Citations

Papers (17)

DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts

CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility

HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding

Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model

HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation

GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction

DreamCube: RGB-D Panorama Generation via Multi-plane Synchronization

R^2-Art: Category-Level Articulation Pose Estimation from Single RGB Image via Cascade Render Strategy

ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-Wise Semantic Alignment and Generation

DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training

Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes

Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds

A Combinatorial Perspective on Transfer Learning

Online Learning in Contextual Bandits using Gated Linear Networks

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars