中文
相关论文

相关论文: VAGS: Velocity Adaptive Guidance Scale for Image E…

200 篇论文

Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing methods exhibit limited exploitation of temporal correlations,…

计算机视觉与模式识别 · 计算机科学 2026-02-11 Xiaoyue Ling , Chuqin Zhou , Chunyi Li , Yunuo Chen , Yuan Tian , Guo Lu , Wenjun Zhang

Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Yan Luo , Drake Du , Hao Huang , Yi Fang , Mengyu Wang

Sampling-based algorithms, which eliminate ''unimportant'' computations during forward and/or back propagation (BP), offer potential solutions to accelerate neural network training. However, since sampling introduces approximations to…

机器学习 · 计算机科学 2024-02-28 Ziteng Wang , Jianfei Chen , Jun Zhu

Counterfactual generation aims to simulate realistic hypothetical outcomes under causal interventions. Diffusion models have emerged as a powerful tool for this task, combining DDIM inversion with conditional generation and classifier-free…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Tian Xia , Fabio De Sousa Ribeiro , Rajat R Rasal , Avinash Kori , Raghav Mehta , Ben Glocker

We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied after normalization.…

机器学习 · 计算机科学 2026-02-12 Francisco Patitucci , Aryan Mokhtari

Vision models are often vulnerable to out-of-distribution (OOD) samples without adapting. While visual prompts offer a lightweight method of input-space adaptation for large-scale vision models, they rely on a high-dimensional additive…

计算机视觉与模式识别 · 计算机科学 2023-10-27 Yun-Yun Tsai , Chengzhi Mao , Junfeng Yang

Generating expressive and diverse human gestures from audio is crucial in fields like human-computer interaction, virtual reality, and animation. Though existing methods have achieved remarkable performance, they often exhibit limitations…

计算机视觉与模式识别 · 计算机科学 2025-02-19 Ming Meng , Ke Mu , Yonggui Zhu , Zhe Zhu , Haoyu Sun , Heyang Yan , Zhaoxin Fan

Text-guided diffusion models have advanced image editing by enabling intuitive control through language. However, despite their strong capabilities, we surprisingly find that SOTA methods struggle with simple, everyday transformations such…

图像与视频处理 · 电气工程与系统科学 2026-03-27 Omar Elezabi , Eduard Zamfir , Zongwei Wu , Radu Timofte

Classifier-Free Guidance (CFG) is essential for high-fidelity conditional generation in flow matching, yet it imposes significant computational overhead by requiring dual forward passes at each sampling step. In this work, we address this…

人工智能 · 计算机科学 2026-05-08 Xin Peng , Ang Gao

Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Yet existing approaches are constrained by their dependence on hand-crafted skills, extensive…

机器人学 · 计算机科学 2026-05-19 Qianzhong Chen , Naixiang Gao , Suning Huang , JunEn Low , Timothy Chen , Jiankai Sun , Mac Schwager

Accuracy and speed are critical in image editing tasks. Pan et al. introduced a drag-based image editing framework that achieves pixel-level control using Generative Adversarial Networks (GANs). A flurry of subsequent studies enhanced this…

计算机视觉与模式识别 · 计算机科学 2024-09-17 Yujun Shi , Jun Hao Liew , Hanshu Yan , Vincent Y. F. Tan , Jiashi Feng

Conventional depth-free multi-view datasets are captured using a moving monocular camera without metric calibration. The scales of camera positions in this monocular setting are ambiguous. Previous methods have acknowledged scale ambiguity…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Fereshteh Forghani , Jason J. Yu , Tristan Aumentado-Armstrong , Konstantinos G. Derpanis , Marcus A. Brubaker

Diffusion-based Handwritten Text Generation (HTG) approaches achieve impressive results on frequent, in-vocabulary words observed at training time and on regular styles. However, they are prone to memorizing training samples and often…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Konstantina Nikolaidou , George Retsinas , Giorgos Sfikas , Silvia Cascianelli , Rita Cucchiara , Marcus Liwicki

Recent advancements in unified image generation models, such as OmniGen, have enabled the handling of diverse image generation and editing tasks within a single framework, accepting multimodal, interleaved texts and images in free form.…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Chao Zhou , Tianyi Wei , Nenghai Yu

Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\textit{e.g., object addition, removal, or modification}).…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Yexin Liu , Wen-Jie Shu , Zile Huang , Haoze Zheng , Yueze Wang , Jingjin Zhu , Manyuan Zhang , Ser-Nam Lim , Harry Yang

Recently, with the rapid advancements of generative models, the field of visual text generation has witnessed significant progress. However, it is still challenging to render high-quality text images in real-world scenarios, as three…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Yuanzhi Zhu , Jiawei Liu , Feiyu Gao , Wenyu Liu , Xinggang Wang , Peng Wang , Fei Huang , Cong Yao , Zhibo Yang

In recent years, data selection has emerged as a core issue for large-scale visual-language model pretraining, especially on noisy web-curated datasets. One widely adopted strategy assigns quality scores such as CLIP similarity for each…

机器学习 · 计算机科学 2024-02-06 Yiping Wang , Yifang Chen , Wendan Yan , Kevin Jamieson , Simon Shaolei Du

Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Zhangkai Wu , Xuhui Fan , Zhongyuan Xie , Kaize Shi , Longbing Cao

The task of Image-to-Video (I2V) generation aims to synthesize a video from a reference image and a text prompt. This requires diffusion models to reconcile high-frequency visual constraints and low-frequency textual guidance during the…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Yuanyang Yin , Yufan Deng , Shenghai Yuan , Kaipeng Zhang , Xiao Yang , Feng Zhao

In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. This paradigm offers substantial improvements in efficiency,…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Zigeng Chen , Xinyin Ma , Gongfan Fang , Xinchao Wang