From Nature Image to Light Field: Light Field Super-Resolution with Hybrid Attention Network

Changguang Wu, Jiangxin Dong, Hao Hou, Jinhui Tang

IEEE TMM

We propose a light field hybrid attention network for high-quality light field image super-resolution, which exploits not only the domain-specific information within the spatial/angular domain but also the spatial-angular correlation across domains.

Frozen LVLMs for Micro-Video Recommendation: A Systematic Study of Feature Extraction and Fusion

Huatuan Sun, Yunshan Ma, Changguang Wu, Yanxin Zhang, Pengfei Wang, Xiaoyu Du

ICMR (Best Paper) 2026

We studies frozen LVLM representations for micro-video recommendation and proposes DFF to effectively fuse multi-layer features with ID embeddings.

Beyond Appearance: Camouflaged Object Detection via Geometric Structure

jinyu Han, Changguang Wu, Fuming Sun, Jinhui Tang

CVPR 2026

We propose the Depth Segment Anything Model (DepthSAM), a MDE-adapted method for camouflaged object detection (COD).

[project]

Sparse Curve Estimation for Real-Time Low-Light Ultra-High-Definition Image Enhancement

Changguang Wu, Jiangxin Dong, Hao Hou, Jinhui Tang

IEEE TCSVT 2026

We present an effective and efficient approach for low-light image enhancement, named Sparse Curve Estimation (SCE).

Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation

Changguang Wu, Jiangxin Dong, Chengjian Li, Jinhui Tang

NeurIPS 2025

We present Plenodium (plenoptic medium), an effective and efficient 3D representation framework capable of jointly modeling both objects and participating media.

[project]