9.2k citations · 16.2k across the 175 of their papers we have counts for
178 papers
TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation
Minheng Ni, Zhengyuan Yang, Yaowen Zhang +9
We study technical image generation, where a model must synthesize information-dense, scientifically precise illustrations from detailed descriptions rather than merely produce vis…
Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
Minheng Ni, Lei Zhang, Zihan Chen +4
Unthinking execution of human instructions in robotic manipulation can lead to severe safety risks, such as poisonings, fires, and even explosions. In this paper, we present respon…
Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning
Minheng Ni, Yutao Fan, Lei Zhang +1
As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in re…
Thin-Plate Spline-based Interpolation for Animation Line Inbetweening
Tianyi Zhu, Wei Shang, Dongwei Ren +1
Animation line inbetweening is a crucial step in animation production aimed at enhancing animation fluidity by predicting intermediate line arts between two key frames. However, ex…
Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors
Wei Shang, Dongwei Ren, Wanying Zhang +3
Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding sp…
MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation
Yuxiang Wei, Zhilong Ji, Jinfeng Bai +3
Text-to-image (T2I) diffusion models have shown significant success in personalized text-to-image generation, which aims to generate novel images with human identities indicated by…
Responsible Visual Editing
Minheng Ni, Yeli Shen, Lei Zhang +1
With recent advancements in visual synthesis, there is a growing risk of encountering images with detrimental effects, such as hate, discrimination, or privacy violations. The rese…
ConSept: Continual Semantic Segmentation via Adapter-based Vision Transformer
Bowen Dong, Guanglei Yang, Wangmeng Zuo +1
In this paper, we delve into the realm of vision transformers for continual semantic segmentation, a problem that has not been sufficiently explored in previous literature. Empiric…
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces
Zhicun Yin, Ming Liu, Xiaoming Li +3
Due to their highly structured characteristics, faces are easier to recover than natural scenes for blind image super-resolution. Therefore, we can extract the degradation represen…
Aggregating Nearest Sharp Features via Hybrid Transformers for Video Deblurring
Wei Shang, Dongwei Ren, Yi Yang +1
Video deblurring methods, aiming at recovering consecutive sharp frames from a given blurry video, usually assume that the input video suffers from consecutively blurry frames. How…
Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration
Yuanshuo Cheng, Mingwen Shao, Yecong Wan +3
Existing Video Restoration (VR) methods always necessitate the individual deployment of models for each adverse weather to remove diverse adverse weather degradations, lacking the…
Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models
Minheng Ni, Yabo Zhang, Kailai Feng +3
Zero-shot referring image segmentation is a challenging task because it aims to find an instance segmentation mask based on the given referring descriptions, without training on th…
VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization
Mingshuai Yao, Yabo Zhang, Xianhui Lin +2
Few-shot font generation is challenging, as it needs to capture the fine-grained stroke styles from a limited set of reference glyphs, and then transfer to other characters, which…
Towards Instance-adaptive Inference for Federated Learning
Chun-Mei Feng, Kai Yu, Nian Liu +3
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. However, the performance of…
Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning
Chun-Mei Feng, Kai Yu, Yong Liu +2
Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper…
UniMAE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving
Jian Zou, Tianyu Huang, Guanglei Yang +4
Masked Autoencoders (MAE) play a pivotal role in learning potent representations, delivering outstanding results across various 3D perception tasks essential for autonomous driving…
Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks
Mingwen Shao, Lingzhuang Meng, Yuanjian Qiao +2
Since the training data of the target model is not available in the black-box substitute attack, most recent schemes utilize GANs to generate data for training the substitute model…
Improving Transferability of Adversarial Examples via Bayesian Attacks
Qizhang Li, Yiwen Guo, Xiaochen Yang +2
The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attentio…
DRM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration
Yuanshuo Cheng, Mingwen Shao, Yecong Wan +1
Existing All-In-One image restoration (IR) methods usually lack flexible modeling on various types of degradation, thus impeding the restoration performance. To achieve All-In-One…
RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution
Renlong Wu, Zhilu Zhang, Shuohao Zhang +2
Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images, which is conducive to enhancing the im…
Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis
Yuxiang Wei, Zhilong Ji, Xiaohe Wu +3
Despite the progress in semantic image synthesis, it remains a challenging problem to generate photo-realistic parts from input semantic map. Integrating part segmentation map can…
ControlVideo: Training-free Controllable Text-to-Video Generation
Yabo Zhang, Yuxiang Wei, Dongsheng Jiang +3
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temp…
Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive
Wei Shang, Dongwei Ren, Chaoyu Feng +3
Modern consumer cameras usually employ the rolling shutter (RS) mechanism, where images are captured by scanning scenes row-by-row, yielding RS distortions for dynamic scenes. To c…
Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation
Yabo Zhang, Zihao Wang, Jun Hao Liew +4
In this work, we investigate performing semantic segmentation solely through the training on image-sentence pairs. Due to the lack of dense annotations, existing text-supervised me…