12 papers · 1 filter
FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining
Jinghong Lan, Wei Cheng, Yunuo Chen +10
Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style r…
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Dong Chen, Fangyun Wei, Ziyu Wan +18
We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters acro…
Adaptive Learned Image Compression with Graph Neural Networks
Yunuo Chen, Bing He, Zezheng Lyu +4
Efficient image compression relies on modeling both local and global redundancy. Most state-of-the-art (SOTA) learned image compression (LIC) methods are based on CNNs or Transform…
Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors
Yunuo Chen, Chuqin Zhou, Jiangchuan Li +5
We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compression. Specifically, we define an ex…
Free-GVC: Towards Training-Free Extreme Generative Video Compression with Temporal Coherence
Xiaoyue Ling, Chuqin Zhou, Chunyi Li +4
Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing metho…
Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures
Chuqin Zhou, Xiaoyue Ling, Yunuo Chen +3
While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate…