Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: NguyenQuang, Sang, HoangVan, Xiem, Peng, Wen-Hsiao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912726429728768
author NguyenQuang, Sang
HoangVan, Xiem
Peng, Wen-Hsiao
author_facet NguyenQuang, Sang
HoangVan, Xiem
Peng, Wen-Hsiao
contents Learned B-frame codecs with hierarchical temporal prediction often encounter the domain-shift issue due to mismatches between the Group-of-Pictures (GOP) sizes for training and testing, leading to inaccurate motion estimates, particularly for large motion. A common solution is to turn large motion into small motion by downsampling video frames during motion estimation. However, determining the optimal downsampling factor typically requires costly rate-distortion optimization. This work introduces lightweight classifiers to predict downsampling factors. These classifiers leverage simple state signals from current and reference frames to balance rate-distortion performance with computational cost. Three variants are proposed: (1) a binary classifier (Bi-Class) trained with Focal Loss to choose between high and low resolutions, (2) a multi-class classifier (Mu-Class) trained with novel soft labels based on rate-distortion costs, and (3) a co-class approach (Co-Class) that combines the predictive capability of the multi-class classifier with the selective search of the binary classifier. All classifier methods can work seamlessly with existing B-frame codecs without requiring codec retraining. Experimental results show that they achieve coding performance comparable to exhaustive search methods while significantly reducing computational complexity. The code is available at: https://github.com/NYCU-MAPL/Fast-OMRA.git.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation
NguyenQuang, Sang
HoangVan, Xiem
Peng, Wen-Hsiao
Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
Learned B-frame codecs with hierarchical temporal prediction often encounter the domain-shift issue due to mismatches between the Group-of-Pictures (GOP) sizes for training and testing, leading to inaccurate motion estimates, particularly for large motion. A common solution is to turn large motion into small motion by downsampling video frames during motion estimation. However, determining the optimal downsampling factor typically requires costly rate-distortion optimization. This work introduces lightweight classifiers to predict downsampling factors. These classifiers leverage simple state signals from current and reference frames to balance rate-distortion performance with computational cost. Three variants are proposed: (1) a binary classifier (Bi-Class) trained with Focal Loss to choose between high and low resolutions, (2) a multi-class classifier (Mu-Class) trained with novel soft labels based on rate-distortion costs, and (3) a co-class approach (Co-Class) that combines the predictive capability of the multi-class classifier with the selective search of the binary classifier. All classifier methods can work seamlessly with existing B-frame codecs without requiring codec retraining. Experimental results show that they achieve coding performance comparable to exhaustive search methods while significantly reducing computational complexity. The code is available at: https://github.com/NYCU-MAPL/Fast-OMRA.git.
title Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation
topic Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2511.18724