Search Results for author: Liang Liao

Found 34 papers, 25 papers with code

Towards Robust Online Domain Adaptive Semantic Segmentation under Adverse Weather Conditions

no code implementations2 Sep 2024 Taorong Liu, Jing Xiao, Liang Liao, Chia-Wen Lin

Online Domain Adaptation (OnDA) is designed to handle unforeseeable domain changes at minimal cost that occur during the deployment of the model, lacking clear boundaries between the domain, such as sudden weather events.

Online Domain Adaptation Semantic Segmentation

Q-Ground: Image Quality Grounding with Large Multi-modality Models

1 code implementation24 Jul 2024 Chaofeng Chen, Sensen Yang, HaoNing Wu, Liang Liao, ZiCheng Zhang, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

Recent advances of large multi-modality models (LMM) have greatly improved the ability of image quality assessment (IQA) method to evaluate and explain the quality of visual content.

Image Quality Assessment

360VFI: A Dataset and Benchmark for Omnidirectional Video Frame Interpolation

no code implementations19 Jul 2024 Wenxuan Lu, Mengshun Hu, Yansheng Qiu, Liang Liao, Zheng Wang

This paper introduces the benchmark dataset, 360VFI, for Omnidirectional Video Frame Interpolation.

Decoder ERP +1

Towards Open-ended Visual Quality Comparison

no code implementations26 Feb 2024 HaoNing Wu, Hanwei Zhu, ZiCheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Annan Wang, Wenxiu Sun, Qiong Yan, Xiaohong Liu, Guangtao Zhai, Shiqi Wang, Weisi Lin

Comparative settings (e. g. pairwise choice, listwise ranking) have been adopted by a wide range of subjective studies for image quality assessment (IQA), as it inherently standardizes the evaluation criteria across different observers and offer more clear-cut responses.

Image Quality Assessment

Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement

1 code implementation CVPR 2024 Kangmin Xu, Liang Liao, Jing Xiao, Chaofeng Chen, HaoNing Wu, Qiong Yan, Weisi Lin

Further we propose a local distortion extractor to obtain local distortion features from the pretrained CNNs and a local distortion injector to inject the local distortion features into ViT.

Image Quality Assessment Inductive Bias +1

Iterative Token Evaluation and Refinement for Real-World Super-Resolution

1 code implementation9 Dec 2023 Chaofeng Chen, Shangchen Zhou, Liang Liao, HaoNing Wu, Wenxiu Sun, Qiong Yan, Weisi Lin

Distortion removal involves simple HQ token prediction with LQ images, while texture generation uses a discrete diffusion model to iteratively refine the distortion removal output with a token refinement network.

Image Super-Resolution Texture Synthesis

Enhancing Diffusion Models with Text-Encoder Reinforcement Learning

1 code implementation27 Nov 2023 Chaofeng Chen, Annan Wang, HaoNing Wu, Liang Liao, Wenxiu Sun, Qiong Yan, Weisi Lin

While fine-tuning the U-Net can partially improve performance, it remains suffering from the suboptimal text encoder.

reinforcement-learning Reinforcement Learning

Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models

2 code implementations CVPR 2024 HaoNing Wu, ZiCheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Annan Wang, Kaixin Xu, Chunyi Li, Jingwen Hou, Guangtao Zhai, Geng Xue, Wenxiu Sun, Qiong Yan, Weisi Lin

Multi-modality foundation models, as represented by GPT-4V, have brought a new paradigm for low-level visual perception and understanding tasks, that can respond to a broad range of natural human instructions in a model.

Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation

1 code implementation31 Oct 2023 Liang Liao, Liang Wan, Mingsheng Liu, Shusheng Li

To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion.

Real-Time Semantic Segmentation

Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision

1 code implementation25 Sep 2023 HaoNing Wu, ZiCheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Annan Wang, Chunyi Li, Wenxiu Sun, Qiong Yan, Guangtao Zhai, Weisi Lin

To address this gap, we present Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment.

Image Quality Assessment

Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment

no code implementations23 Aug 2023 Kangmin Xu, Liang Liao, Jing Xiao, Chaofeng Chen, HaoNing Wu, Qiong Yan, Weisi Lin

Further, we propose a local distortion extractor to obtain local distortion features from the pretrained CNN and a local distortion injector to inject the local distortion features into ViT.

Image Quality Assessment Inductive Bias +1

TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment

1 code implementation6 Aug 2023 Chaofeng Chen, Jiadi Mo, Jingwen Hou, HaoNing Wu, Liang Liao, Wenxiu Sun, Qiong Yan, Weisi Lin

Our approach to IQA involves the design of a heuristic coarse-to-fine network (CFANet) that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner.

Local Distortion Video Quality Assessment

Color Image Recovery Using Generalized Matrix Completion over Higher-Order Finite Dimensional Algebra

no code implementations4 Aug 2023 Liang Liao, Zhuang Guo, Qi Gao, Yan Wang, Fajun Yu, Qifeng Zhao, Stephen Johh Maybank

To improve the accuracy of color image completion with missing entries, we present a recovery method based on generalized higher-order scalars.

Matrix Completion

TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting

1 code implementation20 Jun 2023 Taorong Liu, Liang Liao, Delin Chen, Jing Xiao, Zheng Wang, Chia-Wen Lin, Shin'ichi Satoh

For precise utilization of the reference features for guidance, a reference-patch alignment (Ref-PA) module is proposed to align the patch features of the reference and corrupted images and harmonize their style differences, while a reference-patch transformer (Ref-PT) module is proposed to refine the embedded reference feature.

Decoder Image Inpainting +1

Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach

1 code implementation22 May 2023 HaoNing Wu, Erli Zhang, Liang Liao, Chaofeng Chen, Jingwen Hou, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

Though subjective studies have collected overall quality scores for these videos, how the abstract quality scores relate with specific factors is still obscure, hindering VQA methods from more concrete quality evaluations (e. g. sharpness of a video).

Video Quality Assessment Visual Question Answering (VQA)

GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clustering

1 code implementation CVPR 2023 Weiqing Yan, Yuanyang Zhang, Chenlei Lv, Chang Tang, Guanghui Yue, Liang Liao, Weisi Lin

However, most existing deep clustering methods learn consensus representation or view-specific representations from multiple views via view-wise aggregation way, where they ignore structure relationship of all samples.

Clustering Contrastive Learning +1

Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessment

2 code implementations28 Apr 2023 HaoNing Wu, Liang Liao, Annan Wang, Chaofeng Chen, Jingwen Hou, Wenxiu Sun, Qiong Yan, Weisi Lin

The proliferation of videos collected during in-the-wild natural settings has pushed the development of effective Video Quality Assessment (VQA) methodologies.

Video Quality Assessment Visual Question Answering (VQA)

Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion

2 code implementations26 Feb 2023 HaoNing Wu, Liang Liao, Jingwen Hou, Chaofeng Chen, Erli Zhang, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

Recent learning-based video quality assessment (VQA) algorithms are expensive to implement due to the cost of data collection of human quality opinions, and are less robust across various scenarios due to the biases of these opinions.

Video Quality Assessment Visual Question Answering (VQA)

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

4 code implementations11 Oct 2022 HaoNing Wu, Chaofeng Chen, Liang Liao, Jingwen Hou, Wenxiu Sun, Qiong Yan, Jinwei Gu, Weisi Lin

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.

Ranked #2 on Video Quality Assessment on KoNViD-1k (using extra training data)

Video Quality Assessment Visual Question Answering (VQA)

Reference-Guided Texture and Structure Inference for Image Inpainting

1 code implementation29 Jul 2022 Taorong Liu, Liang Liao, Zheng Wang, Shin'ichi Satoh

Existing learning-based image inpainting methods are still in challenge when facing complex semantic environments and diverse hole patterns.

Decoder Image Inpainting

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

1 code implementation8 Jul 2022 Liang Liao, Kangmin Xu, HaoNing Wu, Chaofeng Chen, Wenxiu Sun, Qiong Yan, Weisi Lin

Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations.

Video Quality Assessment Visual Question Answering (VQA)

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

4 code implementations6 Jul 2022 HaoNing Wu, Chaofeng Chen, Jingwen Hou, Liang Liao, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

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.

Ranked #4 on Video Quality Assessment on LIVE-VQC (using extra training data)

Video Quality Assessment

DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment

1 code implementation20 Jun 2022 HaoNing Wu, Chaofeng Chen, Liang Liao, Jingwen Hou, Wenxiu Sun, Qiong Yan, Weisi Lin

Based on prominent time-series modeling ability of transformers, we propose a novel and effective transformer-based VQA method to tackle these two issues.

Time Series Analysis Video Quality Assessment +1

Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion

1 code implementation10 Jun 2022 Liang Liao, WenYi Chen, Jing Xiao, Zheng Wang, Chia-Wen Lin, Shin'ichi Satoh

Specifically, based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion (TDo-Dif) scheme.

Autonomous Driving Pseudo Label +4

Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning

no code implementations CVPR 2022 Mengshun Hu, Kui Jiang, Liang Liao, Jing Xiao, Junjun Jiang, Zheng Wang

Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction.

Video Reconstruction Video Super-Resolution

Approximation of Images via Generalized Higher Order Singular Value Decomposition over Finite-dimensional Commutative Semisimple Algebra

1 code implementation1 Feb 2022 Liang Liao, Sen Lin, Lun Li, Xiuwei Zhang, Song Zhao, Yan Wang, Xinqiang Wang, Qi Gao, Jingyu Wang

Higher order singular value decomposition (HOSVD) extends the SVD and can approximate higher order data using sums of a few rank-one components.

Generalized Image Reconstruction over T-Algebra

1 code implementation17 Jan 2021 Liang Liao, Xuechun Zhang, Xinqiang Wang, Sen Lin, Xin Liu

We also show in our experiments that the performance of TPCA increases when the order of compounded pixels increases.

Data Compression Dimensionality Reduction +1

Image Inpainting Guided by Coherence Priors of Semantics and Textures

no code implementations CVPR 2021 Liang Liao, Jing Xiao, Zheng Wang, Chia-Wen Lin, Shin'ichi Satoh

In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner.

Image Inpainting Semantic Segmentation

General Data Analytics with Applications to Visual Information Analysis: A Provable Backward-Compatible Semisimple Paradigm over T-Algebra

1 code implementation31 Oct 2020 Liang Liao, Stephen John Maybank

We consider a novel backward-compatible paradigm of general data analytics over a recently-reported semisimple algebra (called t-algebra).

Generalized Visual Information Analysis via Tensorial Algebra

1 code implementation31 Jan 2020 Liang Liao, Stephen John Maybank

Higher order data is modeled using matrices whose entries are numerical arrays of a fixed size.

Cannot find the paper you are looking for? You can Submit a new open access paper.