Dong Liu

16

Papers

87

Total Citations

Papers (16)

Offline and Online Optical Flow Enhancement for Deep Video Compression

HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models

Generalizable Fourier Augmentation for Unsupervised Video Object Segmentation

Neural Video Compression with Context Modulation

Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression

Learned Image Compression with Hierarchical Progressive Context Modeling

StableCodec: Taming One-Step Diffusion for Extreme Image Compression

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation

When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training

Few-Shot Domain Adaptation for Learned Image Compression

Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training

SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling

Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark

Augmented Deep Contexts for Spatially Embedded Video Coding

Arbitrary-Scale Video Super-resolution Guided by Dynamic Context

CTO-SLAM: Contour Tracking for Object-Level Robust 4D SLAM