S4-260095 - AI Summary

Neural Network Based Video Codec Architecture and Support for Error Resilience

Back to Agenda Download Summary
AI-Generated Summary AI

Summary of S4-260095: Neural Network Based Video Codec Architecture and Support for Error Resilience

Document Overview

This contribution proposes documenting neural network-based codec (NNC) architectures and their error resilience capabilities in the 6G Media study (FS_6G_MED). The document focuses on two specific NNC implementations: DVC and GRACE codecs, highlighting their potential relevance for 6G deployments targeting 2030.

Main Technical Contributions

DVC Codec Architecture

The document describes the DVC (Deep Video Compression) codec proposed by Guo Lu et al. (2019), which represents a hybrid approach to neural network-based video coding:

Key Architecture Features:
- Replaces traditional video coding components with neural network equivalents while maintaining the overall predictive coding architecture
- Uses CNN models for optical flow estimation in motion estimation and compression
- Implements neural network-based motion compensation to generate predicted frames
- Maintains functional similarity between traditional and NNC components

Joint Optimization Approach:
The codec jointly trains/optimizes multiple components:
- Motion estimation
- Motion compensation
- Residual compression
- Quantization and bit-rate estimation

Performance:
- Achieves competitive results with H.264 and H.265
- Publicly available source code and research paper
- Similar approaches adopted in industry (Deep Render codec in FFMPEG and VLC)

GRACE Codec and Error Resilience Extensions

The document presents GRACE codec (Yihua Cheng et al. 2025) as an extension of DVC with enhanced error resilience:

Channel-Aware Training:
- Jointly trains encoder and decoder under simulated packet loss conditions
- Enables codec awareness of specific loss patterns
- Implements channel-aware source coding design

Technical Implementation:
- Encodes each frame as a tensor split into independently decodable sub-tensors
- Uses arithmetic coding mapped to packets
- Tested across wide range of loss rates
- Includes lighter profiles (GRACE-lite) for mobile devices

Performance Validation:
- User study with 240 crowdsourced participants
- Tested 61 videos under realistic conditions
- Used Google GCC to emulate WebRTC congestion control
- Channel conditions: LTE and broadband traces (0.2-8 Mbps, 100ms end-to-end delay)
- MOS scores up to 38% better than H.264/H.265 with AL-FEC and error concealment

Key Performance Improvements:
- Exceptional reduction in tail latency
- Reduced non-rendered frames
- Reduced stalls per second
- Improved video smoothness

Hardware Requirements:
- Original GRACE: NVIDIA A40 GPU (31.2-51.2 fps)
- GRACE-lite: Real-time capable on current mobile devices

Identified Limitations

Content Specificity:
- NNC performance may be content-specific due to training data dependencies

Reconstruction Challenges:
- Potential reconstruction failures due to non-bit-exact arithmetic operations in GPU frameworks
- Issues with floating-point arithmetic and convolution operations
- Currently under discussion in SC29 (media standards organization)
- Identified as potential key enabler requiring resolution for future NNC codec adoption

Proposals

The document makes two specific proposals:

  1. Documentation Request: Document NNC features and their application to error-resilient AI traffic in the 6G MED TR under 6G Media (based on clauses 2 and 3)

  2. Use Case Consideration: Include the use case of NNC with channel-aware source coding training in AI traffic characteristics

Text Proposal Structure

The contribution includes specific text proposals for:
- Change 1: Addition of two references to the normative references section
- Change 2: New clause 6.2.4.X under Work topic #2d (AI Traffic Characteristics) containing the technical description of DVC and GRACE codecs, including architecture diagrams and performance characteristics

Document Information
Source:
Huawei Tech.(UK) Co.. Ltd
Type:
pCR
For:
Agreement
Original Document:
View on 3GPP
Title: Neural Network Based Video Codec Architecture and Support for Error Resilience
Agenda item: 11.1
Agenda item description: FS_6G_MED (Study on Media aspects for 6G System)
Doc type: pCR
For action: Agreement
Release: Rel-20
Specification: 26.87
Version: 0.0.1
Related WIs: FS_6G_MED
Spec: 26.87
Contact: Rufail Mekuria
Uploaded: 2026-02-03T08:50:05.980000
Contact ID: 104180
TDoc Status: noted
Reservation date: 02/02/2026 13:42:53
Agenda item sort order: 60