5 papers
Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
Ziyuan Huang, DanDan Zheng, Cheng Zou +13
Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in dis…
Reversing Flow for Image Restoration
Haina Qin, Wenyang Luo, Libin Wang +5
Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation. Existing generative models for image restora…
MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
Shuwei Shi, Biao Gong, Xi Chen +9
The image-to-video (I2V) generation is conditioned on the static image, which has been enhanced recently by the motion intensity as an additional control signal. These motion-aware…
Mimir: Improving Video Diffusion Models for Precise Text Understanding
Shuai Tan, Biao Gong, Yutong Feng +6
Text serves as the key control signal in video generation due to its narrative nature. To render text descriptions into video clips, current video diffusion models borrow features…
Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts
Honglin Li, Yuting Gao, Chenglu Zhu +3
Multimodal large language models (MLLMs) are closing the gap to human visual perception capability rapidly, while, still lag behind on attending to subtle images details or locatin…