Jinwei Gu

9

Papers

103

Total Citations

Papers (9)

AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion

NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images

ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary

Cached Transformers: Improving Transformers with Differentiable Memory Cached

Parallel Sequence Modeling via Generalized Spatial Propagation Network

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions

A Physics-Informed Blur Learning Framework for Imaging Systems

Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal

PolarFree: Polarization-based Reflection-Free Imaging