activity
20242026
collaborators

5 papers

cs.CV2026

CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video

Lingen Li, Guangzhi Wang, Xiaoyu Li +5

Generating high-quality 360° panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially imp…

cs.CV2026

Uni-ISP: Toward Unifying the Learning of ISPs from Multiple Mobile Cameras

Lingen Li, Mingde Yao, Xingyu Meng +3

Modern end-to-end image signal processors (ISPs) can learn complex mappings from RAW/XYZ data to sRGB (and vice versa), opening new possibilities in image processing. However, the…

cs.CV2025

PolarFree: Polarization-based Reflection-free Imaging

Mingde Yao, Menglu Wang, King-Man Tam +3

Reflection removal is challenging due to complex light interactions, where reflections obscure important details and hinder scene understanding. Polarization naturally provides a p…

cs.GR2025

Goal Conditioned Reinforcement Learning for Photo Finishing Tuning

Jiarui Wu, Yujin Wang, Lingen Li +2

Photo finishing tuning aims to automate the manual tuning process of the photo finishing pipeline, like Adobe Lightroom or Darktable. Previous works either use zeroth-order optimiz…

cs.CV2024

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

Lingen Li, Zhaoyang Zhang, Yaowei Li +7

Recent advancements in generative models have significantly improved novel view synthesis (NVS) from multi-view data. However, existing methods depend on external multi-view alignm…