Xin Sun

11

Papers

51

Total Citations

Papers (11)

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

PreciseCam: Precise Camera Control for Text-to-Image Generation

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

Augmented Mass-Spring Model for Real-Time Dense Hair Simulation

ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition

Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints

Multi-view Consistent 3D Panoptic Scene Understanding

Procedure Knowledge Decoupled Distillation Strategy for Procedure Planning in Instructional Videos

OTPNet: ODE-inspired Tuning-free Proximal Network for Remote Sensing Image Fusion

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data