DCNGAN: A Deformable Convolutional-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video

Region-Adaptive Deformable Network for Image Quality Assessment

Image quality assessment (IQA) aims to assess the perceptual quality of images. The outputs of the IQA algorithms are expected to be consistent with human subjective perception. In image restoration and enhancement tasks, images generated by generative adversarial networks (GAN) can achieve better visual performance than traditional CNN-generated images, although they have spatial shift and texture noise. Unfortunately, the existing IQA methods have unsatisfactory performance on the GAN-based distortion partially because of their low tolerance to spatial misalignment. To this end, we propose t…

多场去隔行使用可变形卷积残差块和自注意力

Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention

提出一种多场全帧率去隔行网络，结合可变形卷积残差块和自注意力对齐相邻场特征，在数值和感知性能上达到最先进水平，并位居全帧率排行榜首位。

Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction

A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones. Among them, some restore the missing details of each frame via exploring the spatiotemporal information of neighboring frames. However, these methods usually suffer from a narrow temporal scope, thus may miss some useful details from some frames outside the neighboring ones. In this paper, to boost artifact removal, on the one hand, we propose a Recursive Fusion (RF) module to model the temporal dependency within a long temporal range. Specifically, RF utilizes both th…

超越刚性：非刚性视频编辑基准测试

Beyond Rigid: Benchmarking Non-Rigid Video Editing

提出NRVBench诊断基准，通过物理感知评估框架揭示传统指标在非刚性视频编辑中的不足，并引入VM-Edit基线分析稳定性-可塑性权衡。

一种用于学习视频去隔行和去马赛克的新多图像架构，采用并行可变形卷积和自注意力块

A New Multi-Picture Architecture for Learned Video Deinterlacing and Demosaicing with Parallel Deformable Convolution and Self-Attention Blocks

本文提出一种多图像视频去隔行与去马赛克架构，结合改进的可变形卷积和残差高效top-k自注意力块，利用局部与全局时空相关性，在PSNR、SSIM和感知质量上显著超越现有技术。

GAUGE：面向仿真引擎与视频世界模型物理保真度的、基于测量的基准

GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models

本研究提出基于真实世界的GAUGE基准，联合评估数值仿真器与生成式视频世界模型的物理保真度，发现无统一保真的物理引擎，视频模型存在轨迹形式正确但物理量错误的问题，为开发高保真仿真器奠定基础。