12 papers
StableI2I: Spotting Unintended Changes in Image-to-Image Transition
Jiayang Li, Shuo Cao, Xiaohui Li +6
In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. H…
dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
Yi Xin, Siqi Luo, Tianxiang Xu +13
Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and ef…
Accelerating Masked Image Generation by Learning Latent Controlled Dynamics
Kaiwen Zhu, Quansheng Zeng, Yuandong Pu +8
Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notabl…
Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining
Jinfan Hu, Zhiyuan You, Jinjin Gu +3
Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism of this failure, using im…
PICABench: How Far Are We from Physically Realistic Image Editing?
Yuandong Pu, Le Zhuo, Songhao Han +10
Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond complet…
UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
Shuo Cao, Jiayang Li, Xiaohui Li +12
Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their abil…