12 papers
CodecArena: Codec Quality Assessment via Visual Reinforcement Learning
Jiaye Fu, Weiqi Li, Qiankun Gao +5
Video coding is advancing into the low and ultra-low bitrate regime, driven by end-to-end codecs that replace the hand-crafted pipeline with jointly optimized neural networks and g…
VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought
Xuanyu Zhang, Weiqi Li, Qunliang Xing +6
Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static architectures and fixed inference pipelines often fail to generalize. Recent age…
OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution
Shijie Zhao, Xuanyu Zhang, Bin Chen +8
Aligning generative real-world image super-resolution models with human visual preference is challenging due to the perception--fidelity trade-off and diverse, unknown degradations…
Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution
Bin Chen, Weiqi Li, Shijie Zhao +4
While many diffusion models have achieved impressive results in real-world video super-resolution (Real-VSR) by generating rich and realistic details, their reliance on multi-step…
Audio-Visual Cross-Modal Compression for Generative Face Video Coding
Youmin Xu, Mengxi Guo, Shijie Zhao +4
Generative face video coding (GFVC) is vital for modern applications like video conferencing, yet existing methods primarily focus on video motion while neglecting the significant…
UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement
Weiqi Li, Xuanyu Zhang, Bin Chen +7
Image quality assessment (IQA) and image restoration are fundamental problems in low-level vision. Although IQA and restoration are closely connected conceptually, most existing wo…
Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
Shijie Zhao, Xuanyu Zhang, Weiqi Li +4
Reasoning-based image quality assessment (IQA) models trained through reinforcement learning (RL) exhibit exceptional generalization, yet the underlying mechanisms and critical fac…
VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning
Xuanyu Zhang, Weiqi Li, Shijie Zhao +3
Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-genera…
MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection
Shuyu Wang, Weiqi Li, Qian Wang +2
Recent advances in AI-generated content (AIGC) have significantly accelerated image editing techniques, driving increasing demand for diverse and fine-grained edits. Despite these…
Q-Insight: Understanding Image Quality via Visual Reinforcement Learning
Weiqi Li, Xuanyu Zhang, Shijie Zhao +4
Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generat…
OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation
Weiqi Li, Shijie Zhao, Chong Mou +6
As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generatio…
ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Images
Weiqi Li, Shijie Zhao, Bin Chen +4
With the advent of virtual reality technology, omnidirectional image (ODI) rescaling techniques are increasingly embraced for reducing transmitted and stored file sizes while prese…