Search: diffusion models

More than 1,000 papers match: here are the 1,000 most recent, ranked by relevance.

• Dynamic Eraser for Guided Concept Erasure in Diffusion Models

  Qinghui Gong · 14 April 2026 · Data Stream Mining Techniques

  Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while token-level interventions struggle with semantic granularity a…

• Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models

  Dehui Wang, Rong Wei, Yue Shi, Congsheng Xu, Shoufa Chen, Dingxiang Luo, Tianshuo Yang, Xiaokang Yang, Wei Sui, Yusen Qin, Rui Tang, Yao Mu · 14 April 2026 · Advanced Vision and Imaging

  The growing demand for Embodied AI and VR applications has highlighted the need for synthesizing high-quality 3D indoor scenes from sparse inputs. However, existing approaches struggle to infer massive amounts of missing geometry in large unseen areas while maintaining global consistency, often prod…

• Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models

  Hoigi Seo, Byung Hyun Lee, Jaehyun Cho, Sungjin Lim, Se Young Chun · 14 April 2026 · Generative Adversarial Networks and Image Synthesis

  Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation strategy, yet existing approaches struggle to balance scalability, p…

• Latent-Compressed Variational Autoencoder for Video Diffusion Models

  Jiarui Guan, Wenshuai Zhao, Zhengtao Zou, Juho Kannala, Arno Solin · 14 April 2026 · Generative Adversarial Networks and Image Synthesis

  Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive number of latent channels can impede the convergence of latent d…

• EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model

  Kunho Kim, Sumin Seo, Yongjun Cho, Hyungjin Chung · 14 April 2026 · Generative Adversarial Networks and Image Synthesis

  We propose EditCrafter, a high-resolution image editing method that operates without tuning, leveraging pretrained text-to-image (T2I) diffusion models to process images at resolutions significantly exceeding those used during training. Leveraging the generative priors of large-scale T2I diffusion m…

• Vector Field Synthesis with Sparse Streamlines Using Diffusion Model

  Nguyen K. Phan, Ricardo Morales, Sebastian D. Espriella, Guoning Chen · 14 April 2026 · Model Reduction and Neural Networks

  We present a novel diffusion-based framework for synthesizing 2D vector fields from sparse, coherent inputs (i.e., streamlines) while maintaining physical plausibility. Our method employs a conditional denoising diffusion probabilistic model with classifier-free guidance, enabling progressive recons…

• HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images

  Sungik Choi, Hankook Lee, Jaehoon Lee, Seunghyun Kim, Stanley Jungkyu Choi, Moontae Lee · 14 April 2026 · Advanced Steganography and Watermarking Techniques

  Dramatic advances in the quality of the latent diffusion models (LDMs) also led to the malicious use of AI-generated images. While current AI-generated image detection methods assume the availability of real/AI-generated images for training, this is practically limited given the vast expressibility …

• Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

  Qingyu Shi, Jinbin Bai, Zhuoran Zhao, Wenhao Chai, Kaidong Yu, Jianzong Wu, Shuangyong Song, Yunhai Tong, Xiangtai Li, Xuelong Li, Shuicheng Yan · 14 April 2026 · Generative Adversarial Networks and Image Synthesis

  Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer from slow inference due to sequential decoding, and non-auto…

• Rethinking the Diffusion Model from a Langevin Perspective

  Candi Zheng, Yuan Lan · 14 April 2026 · Flow Experience in Various Fields

  Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically demanding mathematics that can be difficult for beginners to grasp. One classic question is: how does the reverse process invert the forward process …

• Evolutionary Token-Level Prompt Optimization for Diffusion Models

  Dom\'icio Pereira Neto, Jo\~ao Correia, Penousal Machado · 14 April 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-image diffusion models exhibit strong generative performance but remain highly sensitive to prompt formulation, often requiring extensive manual trial and error to obtain satisfactory results. This motivates the development of automated, model-agnostic prompt optimization methods that can sy…

• SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images

  Yuta Matsuzaki, Seiichi Uchida, Shumpei Takezaki · 13 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion models trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address this, we propose SCoRe (Spectral Cutoff Regeneration), a training-free, generation-time spectral regeneration method for clean image generation from di…

• Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models

  Wongi Jeong, Hoigi Seo, Se Young Chun · 13 April 2026 · Generative Adversarial Networks and Image Synthesis

  Image generative models have become indispensable tools to yield exquisite high-resolution (HR) images for everyone, ranging from general users to professional designers. However, a desired outcome often requires generating a large number of HR images with different prompts and seeds, resulting in h…

• BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training

  Thejas Venkatesh, Suguna Varshini Velury · 13 April 2026 · Generative Adversarial Networks and Image Synthesis

  With the rapid adoption of diffusion models, synthetic data generation has emerged as a promising approach for addressing the growing demand for large-scale image datasets. However, images generated purely by diffusion models often exhibit visual inconsistencies, and training models on such data can…

• What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment Reconstruction

  Loc-Phat Truong, Meysam Madadi, Sergio Escalera · 13 April 2026 · Generative Adversarial Networks and Image Synthesis

  Virtual Try-On (VTON) has seen rapid advancements, providing a strong foundation for generative fashion tasks. However, the inverse problem, Virtual Try-Off (VTOFF)-aimed at reconstructing the canonical garment from a draped-on image-remains a less understood domain, distinct from the heavily resear…

• Graph Defense Diffusion Model

  Xin He, Wenqi Fan, Yili Wang, Chengyi Liu, Rui Miao, Xin Juan, Xin Wang · 13 April 2026 · Information and Cyber Security

  Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs. However, they struggle to defend effectively against multiple types of adversarial a…

• Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition

  Yuxi Zhou, Zhengbo Zhang, Jingyu Pan, Zhiyu Lin, Zhigang Tu · 13 April 2026 · Human Pose and Action Recognition

  Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits generalization to novel actions. Zero-Shot Skeleton Action Re…

• When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

  Zhengyang Sun, Yu Chen, Xin Zhou, Xiaofan Li, Xiwu Chen, Dingkang Liang, Xiang Bai · 10 April 2026 · Generative Adversarial Networks and Image Synthesis

  Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA , a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout incons…

• InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation

  Zhefan Rao, Bin Zou, Haoxuan Che, Xuanhua He, Chong Hou Choi, Yanheng Li, Rui Liu, Qifeng Chen · 10 April 2026 · Video Analysis and Summarization

  Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this paper, we show that a video generation backbone can become …

• HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology

  Aasim Bin Saleem, Amr Ahmed, Ardhendu Behera, Hafeezullah Amin, Iman Yi Liao, Mahmoud Khattab, Pan Jia Wern, Haslina Makmur · 10 April 2026 · AI in cancer detection

  Immunohistochemistry (IHC) is essential for assessing specific immune biomarkers like Human Epidermal growth-factor Receptor 2 (HER2) in breast cancer. However, the traditional protocols of obtaining IHC stains are resource-intensive, time-consuming, and prone to structural damages. Virtual staining…

• DiffVC: A Non-autoregressive Framework Based on Diffusion Model for Video Captioning

  Junbo Wang, Liangyu Fu, Yuke Li, Yining Zhu, Ya Jing, Xuecheng Wu, Jiangbin Zheng · 10 April 2026 · Multimodal Machine Learning Applications

  Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore, the few non-autoregressive counterparts suffer from deficienci…

• Guiding a Diffusion Model by Swapping Its Tokens

  Weijia Zhang, Yuehao Liu, Shanyan Guan, Wu Ran, Yanhao Ge, Wei Li, Chao Ma · 10 April 2026 · Advanced Neuroimaging Techniques and Applications

  Classifier-Free Guidance (CFG) is a widely used inference-time technique to boost the image quality of diffusion models. Yet, its reliance on text conditions prevents its use in unconditional generation. We propose a simple method to enable CFG-like guidance for both conditional and unconditional ge…

• FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding

  Jinghan Yang, Yihe Fan, Xudong Pan, Min Yang · 10 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content. Existing NSFW detection methods mainly operate either before or after image generation. Pre-generation methods rely on text prompts and struggle w…

• DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models

  Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu, Dong Xu · 10 April 2026 · Multimodal Machine Learning Applications

  We demonstrate that pre-trained text-to-image diffusion models, despite being trained on raster images, possess a remarkable capacity to guide vector sketch synthesis. In this paper, we introduce DiffSketcher, a novel algorithm for generating vectorized free-hand sketches directly from natural langu…

• FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling

  Shivanshu Shekhar, Sagnik Mukherjee, Jia Yi Zhang, Tong Zhang · 10 April 2026 · Generative Adversarial Networks and Image Synthesis

  We introduce Fleming-Viot Diffusion (FVD), an inference-time alignment method that resolves the diversity collapse commonly observed in Sequential Monte Carlo (SMC) based diffusion samplers. Existing SMC-based diffusion samplers often rely on multinomial resampling or closely related resampling sche…

• Single-Stage Signal Attenuation Diffusion Model for Low-Light Image Enhancement and Denoising

  Ying Liu, Junchao Zhang, Caiyun Wu · 8 April 2026 · Image Enhancement Techniques

  Diffusion models excel at image restoration via probabilistic modeling of forward noise addition and reverse denoising, and their ability to handle complex noise while preserving fine details makes them well-suited for Low-Light Image Enhancement (LLIE). Mainstream diffusion based LLIE methods eithe…