7 papers
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…
ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement
Yufeng Yang, Jianzhuang Liu, Jisheng Chu +4
Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability a…
GEditBench v2: A Human-Aligned Benchmark for General Image Editing
Zhangqi Jiang, Zheng Sun, Xianfang Zeng +7
Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks…
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
Yufeng Yang, Xianfang Zeng, Zhangqi Jiang +8
Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often lim…
DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Loss
Jing Yang, Yufeng Yang
Recent advancements in 2D and 3D generative models have expanded the capabilities of computer vision. However, generating high-quality 4D dynamic content from a single static image…
Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints
Jing Yang, Kaitong Cai, Yijia Fan +2
Full fine-tuning of Large Language Models (LLMs) is notoriously memory-intensive, primarily because conventional optimizers such as SGD or Adam assume access to exact gradients der…