Cheng Lin

9

Papers

25

Total Citations

Papers (9)

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

CADDreamer: CAD Object Generation from Single-view Images

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

NeurIPS 2025arXiv

MAGE : Single Image to Material-Aware 3D via the Multi-View G-Buffer Estimation Model

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation

AIRA: Activation-Informed Low-Rank Adaptation for Large Models