Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment

by   Haoning Wu, et al.

The increased resolution of real-world videos presents a dilemma between efficiency and accuracy for deep Video Quality Assessment (VQA). On the one hand, keeping the original resolution will lead to unacceptable computational costs. On the other hand, existing practices, such as resizing and cropping, will change the quality of original videos due to the loss of details and contents, and are therefore harmful to quality assessment. With the obtained insight from the study of spatial-temporal redundancy in the human visual system and visual coding theory, we observe that quality information around a neighbourhood is typically similar, motivating us to investigate an effective quality-sensitive neighbourhood representatives scheme for VQA. In this work, we propose a unified scheme, spatial-temporal grid mini-cube sampling (St-GMS) to get a novel type of sample, named fragments. Full-resolution videos are first divided into mini-cubes with preset spatial-temporal grids, then the temporal-aligned quality representatives are sampled to compose the fragments that serve as inputs for VQA. In addition, we design the Fragment Attention Network (FANet), a network architecture tailored specifically for fragments. With fragments and FANet, the proposed efficient end-to-end FAST-VQA and FasterVQA achieve significantly better performance than existing approaches on all VQA benchmarks while requiring only 1/1612 FLOPs compared to the current state-of-the-art. Codes, models and demos are available at


page 2

page 4

page 5

page 6

page 13


FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling

Current deep video quality assessment (VQA) methods are usually with hig...

Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancement

Recently, Users Generated Content (UGC) videos becomes ubiquitous in our...

MRET: Multi-resolution Transformer for Video Quality Assessment

No-reference video quality assessment (NR-VQA) for user generated conten...

DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment

The temporal relationships between frames and their influences on video ...

Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment

With the rapid growth of in-the-wild videos taken by non-specialists, bl...

Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models

Blind video quality assessment (BVQA) plays an indispensable role in mon...

StarVQA+: Co-training Space-Time Attention for Video Quality Assessment

Self-attention based Transformer has achieved great success in many comp...

Please sign up or login with your details

Forgot password? Click here to reset