Yu-Lun Liu

Assistant Professor@National Yang Ming Chiao Tung University·中国台湾·OpenReview

研究方向

Novel view synthesis · video stabilization · disparity estimation · Reflection removal · video frame interpolation · HDR reconstruction · computer vision

Yu-Lun Liu

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Voxify3D: From Mesh to Voxel Art with Palette Discretization and Semantic Guidance

Exposing VLM Memorization of Famous Landmarks: A 55K Building Age Dataset Revealing Popularity Bias

A Generative Diffusion Framework for Single Image Reflection Separation

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

FIPER: Factorized Features for Robust Image Super-Resolution and Compression

CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression

DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models

FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors

SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes

FIPER: Generalizable Factorized Fields for Joint Image Compression and Super-Resolution

DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation

360-InpaintR: Reference-Guided 3D Inpainting for Unbounded Scenes