10 papers
Deep Light Pollution Removal in Night Cityscape Photographs
Hao Wang, Xiaolin Wu, Xi Zhang +1
Nighttime photography is severely degraded by light pollution induced by pervasive artificial lighting in urban environments. After long-range scattering and spatial diffusion, unw…
Anisotropic Pooling for LUT-realizable CNN Image Restoration
Xi Zhang, Xiaolin Wu
Table look-up realization of image restoration CNNs has the potential of achieving competitive image quality while being much faster and resource frugal than the straightforward CN…
Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks
Xi Zhang, Xiaolin Wu
Recently, several look-up table (LUT) methods were developed to greatly expedite the inference of CNNs in a classical strategy of trading space for speed. However, these LUT method…
Class-Invariant Test-Time Augmentation for Domain Generalization
Zhicheng Lin, Xiaolin Wu, Xi Zhang
Deep models often suffer significant performance degradation under distribution shifts. Domain generalization (DG) seeks to mitigate this challenge by enabling models to generalize…
Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
Xi Zhang, Xiaolin Wu, Jiamang Wang +1
Large Language Models (LLMs) have demonstrated remarkable capabilities but typically require extensive computational resources and memory for inference. Post-training quantization…
Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization
Hao Xu, Xiaolin Wu, Xi Zhang
3D Gaussian Splatting (3DGS) is rapidly gaining popularity for its photorealistic rendering quality and real-time performance, but it generates massive amounts of data. Hence compr…
Learning Hierarchical Sparse Transform Coding for 3DGS Compression
Hao Xu, Xiaolin Wu, Xi Zhang
Current 3DGS compression methods largely forego the neural analysis-synthesis transform, which is a crucial component in learned signal compression systems. As a result, redundancy…
Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression
Xi Zhang, Xiaolin Wu
It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high co…
Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement
Hao Xu, Xi Zhang, Xiaolin Wu
Compressing a set of unordered points is far more challenging than compressing images/videos of regular sample grids, because of the difficulties in characterizing neighboring rela…
FLLIC: Functionally Lossless Image Compression
Xi Zhang, Xiaolin Wu
Recently, DNN models for lossless image coding have surpassed their traditional counterparts in compression performance, reducing the previous lossless bit rate by about ten percen…