Jingbo Wang

29

Papers

295

Total Citations

Papers (29)

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model

Unified Human-Scene Interaction via Prompted Chain-of-Contacts

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios

DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters

DreamRelation: Bridging Customization and Relation Generation

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions

ARMO: Autoregressive Rigging for Multi-Category Objects

Learning a Discriminative Feature Network for Semantic Segmentation

An End-To-End Network for Panoptic Segmentation

Context Prior for Scene Segmentation

Scene-Aware Generative Network for Human Motion Synthesis

Towards Diverse and Natural Scene-Aware 3D Human Motion Synthesis

DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-Centric Rendering

Learning Human Dynamics in Autonomous Driving Scenarios

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Motion Guided 3D Pose Estimation from Videos

Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing

Point Scene Understanding via Disentangled Instance Mesh Reconstruction

"Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition"

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

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Cinematic Behavior Transfer via NeRF-based Differentiable Filming

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

Group Contextual Encoding for 3D Point Clouds

Compressible-composable NeRF via Rank-residual Decomposition