6 papers · 1 filter
End-to-End Joint Training of Super-Resolution and Compression Artifact Removal for Industrial Machine Vision
Dang BuiDinh, Sang NguyenQuang, Anh NguyenPhuong +2
In industrial machine vision, images captured by edge devices are often downsampled and compressed to reduce bandwidth, introducing resolution loss and compression artifacts that s…
Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting
He-Bi Yang, Jing-Zhong Chen, Yen-Kuan Ho +5
While 3D Gaussian Splatting (3DGS) achieves impressive real-time rendering, it frequently struggles to synthesize high-frequency textures, a limitation heavily exacerbated in memor…
Compressed Video Quality Enhancement: Classifying and Benchmarking over Standards
Xiem HoangVan, Dang BuiDinh, Sang NguyenQuang +1
Compressed video quality enhancement (CVQE) is crucial for improving user experience with lossy video codecs like H.264/AVC, H.265/HEVC, and H.266/VVC. While deep learning based CV…
A Rate-Quality Model for Learned Video Coding
Sang NguyenQuang, Cheng-Wei Chen, Xiem HoangVan +1
Learned video coding (LVC) has recently achieved superior coding performance. In this paper, we model the rate-quality (R-Q) relationship for learned video coding by a parametric f…
Enhancing Quality for VVC Compressed Videos with Omniscient Quality Enhancement Model
Xiem HoangVan, Hieu Bui Minh, Sang NguyenQuang +1
The latest video coding standard H.266/VVC has shown its great improvement in terms of compression performance when compared to its predecessor HEVC standard. Though VVC was implem…
Fast-OMRA: Fast Online Motion Resolution Adaptation for Neural B-Frame Coding
Sang NguyenQuang, Zong-Lin Gao, Kuan-Wei Ho +2
Most learned B-frame codecs with hierarchical temporal prediction suffer from the domain shift issue caused by the discrepancy in the Group-of-Pictures (GOP) size used for training…