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

6 Jul 2022  ·  HaoNing Wu, Chaofeng Chen, Jingwen Hou, Liang Liao, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin ·

Current deep video quality assessment (VQA) methods are usually with high computational costs when evaluating high-resolution videos. This cost hinders them from learning better video-quality-related representations via end-to-end training. Existing approaches typically consider naive sampling to reduce the computational cost, such as resizing and cropping. However, they obviously corrupt quality-related information in videos and are thus not optimal for learning good representations for VQA. Therefore, there is an eager need to design a new quality-retained sampling scheme for VQA. In this paper, we propose Grid Mini-patch Sampling (GMS), which allows consideration of local quality by sampling patches at their raw resolution and covers global quality with contextual relations via mini-patches sampled in uniform grids. These mini-patches are spliced and aligned temporally, named as fragments. We further build the Fragment Attention Network (FANet) specially designed to accommodate fragments as inputs. Consisting of fragments and FANet, the proposed FrAgment Sample Transformer for VQA (FAST-VQA) enables efficient end-to-end deep VQA and learns effective video-quality-related representations. It improves state-of-the-art accuracy by around 10% while reducing 99.5% FLOPs on 1080P high-resolution videos. The newly learned video-quality-related representations can also be transferred into smaller VQA datasets, boosting performance in these scenarios. Extensive experiments show that FAST-VQA has good performance on inputs of various resolutions while retaining high efficiency. We publish our code at https://github.com/timothyhtimothy/FAST-VQA.

PDF Abstract

Results from the Paper


 Ranked #1 on Video Quality Assessment on YouTube-UGC (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Video Quality Assessment KoNViD-1k FAST-VQA (trained on LSVQ only) PLCC 0.855 # 2
Video Quality Assessment KoNViD-1k FAST-VQA (finetuned on KonViD-1k) PLCC 0.892 # 1
Video Quality Assessment LIVE-FB LSVQ FAST-VQA PLCC 0.877 # 1
Video Quality Assessment LIVE-VQC FAST-VQA (finetuned on LIVE-VQC) PLCC 0.862 # 1
Video Quality Assessment LIVE-VQC FAST-VQA (trained on LSVQ only) PLCC 0.844 # 2
Video Quality Assessment YouTube-UGC FAST-VQA (finetuned on YouTube-UGC) PLCC 0.852 # 1
Video Quality Assessment YouTube-UGC FAST-VQA (trained on LSVQ only) PLCC 0.748 # 6

Methods