Generative Adversarial Networks and Image Synthesis

Últimos artículos

• EasyV2V: A High-quality Instruction-based Video Editing Framework

  Jinjie Mai, Chaoyang Wang, Guocheng Gordon Qian, Willi Menapace, Sergey Tulyakov, Bernard Ghanem, Peter Wonka, Ashkan Mirzaei · 19 de diciembre de 2025

  While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a simple and effective framework for instruction-based video editi…

• Using Gaussian Splats to Create High-Fidelity Facial Geometry and Texture

  Haodi He, Jihun Yu, Ronald Fedkiw · 19 de diciembre de 2025

  We leverage increasingly popular three-dimensional neural representations in order to construct a unified and consistent explanation of a collection of uncalibrated images of the human face. Our approach utilizes Gaussian Splatting, since it is more explicit and thus more amenable to constraints tha…

• SFTok: Bridging the Performance Gap in Discrete Tokenizers

  Qihang Rao, Borui Zhang, Wenzhao Zheng, Jie Zhou, Jiwen Lu · 19 de diciembre de 2025

  Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in lower-dimensional spaces, thereby improving computational efficiency…

• TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

  Jintao Zhang, Kaiwen Zheng, Kai Jiang, Haoxu Wang, Ion Stoica, Joseph E. Gonzalez, Jianfei Chen, Jun Zhu · 19 de diciembre de 2025

  We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1) Attention acceleration: TurboDiffusion uses low-bit SageAtten…

• TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering

  Rui Gui, Yang Wan, Haochen Han, Dongxing Mao, Fangming Liu, Min Li, Alex Jinpeng Wang · 19 de diciembre de 2025

  Text rendering has recently emerged as one of the most challenging frontiers in visual generation, drawing significant attention from large-scale diffusion and multimodal models. However, text editing within images remains largely unexplored, as it requires generating legible characters while preser…

• Yuan-TecSwin: A text conditioned Diffusion model with Swin-transformer blocks

  Shaohua Wu, Tong Yu, Shenling Wang, Xudong Zhao · 19 de diciembre de 2025

  Diffusion models have shown remarkable capacity in image synthesis based on their U-shaped architecture and convolutional neural networks (CNN) as basic blocks. The locality of the convolution operation in CNN may limit the model's ability to understand long-range semantic information. To address th…

• PMMD: A pose-guided multi-view multi-modal diffusion for person generation

  Ziyu Shang, Haoran Liu, Rongchao Zhang, Zhiqian Wei, Tongtong Feng · 18 de diciembre de 2025

  Generating consistent human images with controllable pose and appearance is essential for applications in virtual try on, image editing, and digital human creation. Current methods often suffer from occlusions, garment style drift, and pose misalignment. We propose Pose-guided Multi-view Multimodal …

• MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness

  JaeHyuck Choi, MinJun Kim, JeHyeong Hong · 18 de diciembre de 2025

  Few-shot anomaly generation is a key challenge in industrial quality control. Although diffusion models are promising, existing methods struggle: global prompt-guided approaches corrupt normal regions, and existing inpainting-based methods often lack the in-distribution diversity essential for robus…

• IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning

  Yuanhang Li, Yiren Song, Junzhe Bai, Xinran Liang, Hu Yang, Libiao Jin, Qi Mao · 18 de diciembre de 2025

  We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal consistency. Video VFX editing is highly challenging because injecte…

• Physics-Informed Time-Integrated DeepONet: Temporal Tangent Space Operator Learning for High-Accuracy Inference

  Luis Mandl, Dibyajyoti Nayak, Tim Ricken, Somdatta Goswami · 18 de diciembre de 2025

  Accurately modeling and inferring solutions to time-dependent partial differential equations (PDEs) over extended horizons remains a core challenge in scientific machine learning. Traditional full rollout (FR) methods, which predict entire trajectories in one pass, often fail to capture the causal d…

• Softly Constrained Denoisers for Diffusion Models

  Victor M. Yeom Song, Severi Rissanen, Arno Solin, Samuel Kaski, Mingfei Sun · 18 de diciembre de 2025

  Diffusion models struggle to produce samples that respect constraints, a common requirement in scientific applications. Recent approaches have introduced regularization terms in the loss or guidance methods during sampling to enforce such constraints, but they bias the generative model away from the…

• SoFlow: Solution Flow Models for One-Step Generative Modeling

  Tianze Luo, Haotian Yuan, Zhuang Liu · 18 de diciembre de 2025

  The multi-step denoising process in diffusion and Flow Matching models causes major efficiency issues, which motivates research on few-step generation. We present Solution Flow Models (SoFlow), a framework for one-step generation from scratch. By analyzing the relationship between the velocity funct…

• FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows

  Yeonwoo Cha, Semin Kim, Jinhyeon Kwon, Seunghoon Hong · 18 de diciembre de 2025

  Any-to-any generation seeks to translate between arbitrary subsets of modalities, enabling flexible cross-modal synthesis. Despite recent success, existing flow-based approaches are challenged by their inefficiency, as they require large-scale datasets often with restrictive pairing constraints, inc…

• TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation

  Zhenzhi Wang, Jian Wang, Ke Ma, Dahua Lin, Bing Zhou · 18 de diciembre de 2025

  We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While current state-of-the-art systems rely on closed data or compute-heavy models, TalkVerse offers 2.3 million high-resolutio…

• Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting

  Neeraj Sarna, Yuanyuan Li, Michael von Gablenz · 18 de diciembre de 2025

  Large scale text-to-image generation models can memorize and reproduce their training dataset. Since the training dataset often contains copyrighted material, reproduction of training dataset poses a copyright infringement risk, which could result in legal liabilities and financial losses for both t…

• FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videos

  Zhaolun Li, Jichang Li, Yinqi Cai, Junye Chen, Xiaonan Luo, Guanbin Li, Rushi Lan · 17 de diciembre de 2025

  In this paper, we propose FakeRadar, a novel deepfake video detection framework designed to address the challenges of cross-domain generalization in real-world scenarios. Existing detection methods typically rely on manipulation-specific cues, performing well on known forgery types but exhibiting se…

• Generative AI for Video Translation: A Scalable Architecture for Multilingual Video Conferencing

  Amirkia Rafiei Oskooei, Eren Caglar, Ibrahim Sahin, Ayse Kayabay, Mehmet S. Aktas · 17 de diciembre de 2025

  The real-time deployment of cascaded generative AI pipelines for applications like video translation is constrained by significant system-level challenges. These include the cumulative latency of sequential model inference and the quadratic ($\mathcal{O}(N^2)$) computational complexity that renders …

• Random-Bridges as Stochastic Transports for Generative Models

  Stefano Goria, Levent A. Meng\"ut\"urk, Murat C. Meng\"ut\"urk, Berkan Sesen · 17 de diciembre de 2025

  This paper motivates the use of random-bridges -- stochastic processes conditioned to take target distributions at fixed timepoints -- in the realm of generative modelling. Herein, random-bridges can act as stochastic transports between two probability distributions when appropriately initialized, a…

• Understanding Sampler Stochasticity in Training Diffusion Models for RLHF

  Jiayuan Sheng, Hanyang Zhao, Haoxian Chen, David D. Yao, Wenpin Tang · 17 de diciembre de 2025

  Reinforcement Learning from Human Feedback (RLHF) is increasingly used to fine-tune diffusion models, but a key challenge arises from the mismatch between stochastic samplers used during training and deterministic samplers used during inference. In practice, models are fine-tuned using stochastic SD…

• One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation

  Yuan Gao, Chen Chen, Tianrong Chen, Jiatao Gu · 17 de diciembre de 2025

  Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual representations, either by aligning them inside VAEs or direct…

• Improving the Accuracy of Amortized Model Comparison with Self-Consistency

  \v{S}imon Kucharsk\'y, Aayush Mishra, Daniel Habermann, Stefan T. Radev, Paul-Christian B\"urkner · 17 de diciembre de 2025

  Amortized Bayesian inference (ABI) offers fast, scalable approximations to posterior densities by training neural surrogates on data simulated from the statistical model. However, ABI methods are highly sensitive to model misspecification: when observed data fall outside the training distribution (g…

• Towards Transferable Defense Against Malicious Image Edits

  Jie Zhang, Shuai Dong, Shiguang Shan, Xilin Chen · 17 de diciembre de 2025

  Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited transferability in cross-model evaluations. To address this, we pro…

• Generative Spatiotemporal Data Augmentation

  Jinfan Zhou, Lixin Luo, Sungmin Eum, Heesung Kwon, Jeong Joon Park · 16 de diciembre de 2025

  We explore spatiotemporal data augmentation using video foundation models to diversify both camera viewpoints and scene dynamics. Unlike existing approaches based on simple geometric transforms or appearance perturbations, our method leverages off-the-shelf video diffusion models to generate realist…

• Qonvolution: Towards Learning High-Frequency Signals with Queried Convolution

  Abhinav Kumar, Tristan Aumentado-Armstrong, Lazar Valkov, Gopal Sharma, Alex Levinshtein, Radek Grzeszczuk, Suren Kumar · 16 de diciembre de 2025

  Accurately learning high-frequency signals is a challenge in computer vision and graphics, as neural networks often struggle with these signals due to spectral bias or optimization difficulties. While current techniques like Fourier encodings have made great strides in improving performance, there r…

• Variational Learning of Disentangled Representations

  Yuli Slavutsky, Ozgur Beker, David Blei, Bianca Dumitrascu · 16 de diciembre de 2025

  Disentangled representations enable models to separate factors of variation that are shared across experimental conditions from those that are condition-specific. This separation is essential in domains such as biomedical data analysis, where generalization to new treatments, patients, or species de…