Generative Adversarial Networks and Image Synthesis

Últimos artículos

• Generative models for decision-making under distributional shift

  Xiuyuan Cheng, Yunqin Zhu, Yao Xie · 7 de abril de 2026

  Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distribution that may be shifted, context-dependent, partially observed, or stress-induced. This tutorial presents modern generati…

• ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention

  Huiguo He, Pengyu Yan, Ziqi Yi, Weizhi Zhong, Zheng Liu, Yejun Tang, Huan Yang, Guanbin Li, Lianwen Jin · 7 de abril de 2026

  Drag-based image editing enables intuitive visual manipulation through point-based drag operations. Existing methods mainly rely on diffusion inversion or pixel-space warping with inpainting. However, inversion inherently introduces approximation errors that degrade texture fidelity, whereas rigid p…

• Isokinetic Flow Matching for Pathwise Straightening of Generative Flows

  Tauhid Khan · 7 de abril de 2026

  Flow Matching (FM) constructs linear conditional probability paths, but the learned marginal velocity field inevitably exhibits strong curvature due to trajectory superposition. This curvature severely inflates numerical truncation errors, bottlenecking few-step sampling. To overcome this, we introd…

• Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro

  Kenan Tang, Praveen Arunshankar, Andong Hua, Anthony Yang, Yao Qin · 7 de abril de 2026

  The multi-step, iterative image editing capabilities of multi-modal agentic systems have transformed digital content creation. Although latest image editing models faithfully follow instructions and generate high-quality images in single-turn edits, we identify a critical weakness in multi-turn edit…

• ExpressEdit: Fast Editing of Stylized Facial Expressions with Diffusion Models in Photoshop

  Kenan Tang, Jiasheng Guo, Jeffrey Lin, Yao Qin · 7 de abril de 2026

  Facial expressions of characters are a vital component of visual storytelling. While current AI image editing models hold promise for assisting artists in the task of stylized expression editing, these models introduce global noise and pixel drift into the edited image, preventing the integration of…

• Your Pre-trained Diffusion Model Secretly Knows Restoration

  Sudarshan Rajagopalan, Vishal M. Patel · 7 de abril de 2026

  Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. However, diffusion-based restoration methods primarily rely on fine-tuning or Control-Net style modules to leverage the pre-trained diffusion …

• Common Inpainted Objects In-N-Out of Context

  Tianze Yang, Tyson Jordan, Ruitong Sun, Ninghao Liu, Jin Sun · 7 de abril de 2026

  We present Common Inpainted Objects In-N-Out of Context (COinCO), a novel dataset addressing the scarcity of out-of-context examples in existing vision datasets. By systematically replacing objects in COCO images through diffusion-based inpainting, we create 97,722 unique images featuring both conte…

• Generative Modeling under Non-Monotonic MAR Missingness via Approximate Wasserstein Gradient Flows

  Gitte Kremling, Jeffrey N\"af, Johannes Lederer · 7 de abril de 2026

  The prevalence of missing values in data science poses a substantial risk to any further analyses. Despite a wealth of research, principled nonparametric methods to deal with general non-monotone missingness are still scarce. Instead, ad-hoc imputation methods are often used, for which it remains un…

• Deep Kuratowski Embedding Neural Networks for Wasserstein Metric Learning

  Andrew Qing He · 7 de abril de 2026

  Computing pairwise Wasserstein distances is a fundamental bottleneck in data analysis pipelines. Motivated by the classical Kuratowski embedding theorem, we propose two neural architectures for learning to approximate the Wasserstein-2 distance ($W_2$) from data. The first, DeepKENN, aggregates dist…

• BLK-Assist: A Methodological Framework for Artist-Led Co-Creation with Generative AI Models

  Daniel Grimes, Rachel M. Harrison · 7 de abril de 2026

  This paper presents BLK-Assist, a modular framework for artist-specific fine-tuning of diffusion models using parameter-efficient methods. The system is implemented as a case study with a single professional artist's proprietary corpus and consists of three components: BLK-Conceptor (LoRA-adapted co…

• Multi-Component VAE with Gaussian Markov Random Field

  Fouad Oubari, Mohamed El-Baha, Raphael Meunier, Rodrigue D\'ecatoire, Mathilde Mougeot · 7 de abril de 2026

  Multi-component datasets with intricate dependencies, like industrial assemblies or multi-modal imaging, challenge current generative modeling techniques. Existing Multi-component Variational AutoEncoders typically rely on simplified aggregation strategies, neglecting critical nuances and consequent…

• Stochastic Generative Plug-and-Play Priors

  Chicago Y. Park, Edward P. Chandler, Yuyang Hu, Michael T. McCann, Cristina Garcia-Cardona, Brendt Wohlberg, Ulugbek S. Kamilov · 7 de abril de 2026

  Plug-and-play (PnP) methods are widely used for solving imaging inverse problems by incorporating a denoiser into optimization algorithms. Score-based diffusion models (SBDMs) have recently demonstrated strong generative performance through a denoiser trained across a wide range of noise levels. Des…

• GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction

  Yedong Shen, Shiqi Zhang, Sha Zhang, Yifan Duan, Xinran Zhang, Wenhao Yu, Lu Zhang, Jiajun Deng, Yanyong Zhang · 7 de abril de 2026

  Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction, limiting the ability to recover regions occluded by dynamic…

• Spectral Path Regression: Directional Chebyshev Harmonics for Interpretable Tabular Learning

  Milo Coombs · 7 de abril de 2026

  Classical approximation bases such as Chebyshev polynomials provide principled and interpretable representations, but their multivariate tensor-product constructions scale exponentially with dimension and impose axis-aligned structure that is poorly matched to real tabular data. We address this by r…

• Training-Free Refinement of Flow Matching with Divergence-based Sampling

  Yeonwoo Cha, Jaehoon Yoo, Semin Kim, Yunseo Park, Jinhyeon Kwon, Seunghoon Hong · 7 de abril de 2026

  Flow-based models learn a target distribution by modeling a marginal velocity field, defined as the average of sample-wise velocities connecting each sample from a simple prior to the target data. When sample-wise velocities conflict at the same intermediate state, however, this averaged velocity ca…

• Category-based Galaxy Image Generation via Diffusion Models

  Xingzhong Fan, Hongming Tang, Yue Zeng, M. B. N. Kouwenhoven, Guangquan Zeng · 6 de abril de 2026

  Conventional galaxy generation methods rely on semi-analytical models and hydrodynamic simulations, which are highly dependent on physical assumptions and parameter tuning. In contrast, data-driven generative models do not have explicit physical parameters pre-determined, and instead learn them effi…

• LumiVideo: An Intelligent Agentic System for Video Color Grading

  Yuchen Guo, Junli Gong, Hongmin Cai, Yiu-ming Cheung, Weifeng Su · 6 de abril de 2026

  Video color grading is a critical post-production process that transforms flat, log-encoded raw footage into emotionally resonant cinematic visuals. Existing automated methods act as static, black-box executors that directly output edited pixels, lacking both interpretability and the iterative contr…

• Conditional Sampling via Wasserstein Autoencoders and Triangular Transport

  Mohammad Al-Jarrah, Michele Martino, Marcus Yim, Bamdad Hosseini, Amirhossein Taghvaei · 6 de abril de 2026

  We present Conditional Wasserstein Autoencoders (CWAEs), a framework for conditional simulation that exploits low-dimensional structure in both the conditioned and the conditioning variables. The key idea is to modify a Wasserstein autoencoder to use a (block-) triangular decoder and impose an appro…

• VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation

  Mengtian Li, Yuwei Lu, Feifei Li, Chenqi Gan, Zhifeng Xie, Xi Wang · 6 de abril de 2026

  Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generative camera systems can produce diverse, text-conditioned trajectories, but they lack this "director in the loop" and hav…

• Diffusion Models as Dataset Distillation Priors

  Duo Su, Huyu Wu, Huanran Chen, Yiming Shi, Yuzhu Wang, Xi Ye, Jun Zhu · 6 de abril de 2026

  Dataset distillation aims to synthesize compact yet informative datasets from large ones. A significant challenge in this field is achieving a trifecta of diversity, generalization, and representativeness in a single distilled dataset. Although recent generative dataset distillation methods adopt po…

• Understanding Latent Diffusability via Fisher Geometry

  Jing Gu, Morteza Mardani, Wonjun Lee, Dongmian Zou, Gilad Lerman · 6 de abril de 2026

  Diffusion models often degrade when trained in latent spaces (e.g., VAEs), yet the formal causes remain poorly understood. We quantify latent-space diffusability through the rate of change of the Minimum Mean Squared Error (MMSE) along the diffusion trajectory. Our framework decomposes this MMSE rat…

• Learning from Synthetic Data via Provenance-Based Input Gradient Guidance

  Koshiro Nagano, Ryo Fujii, Ryo Hachiuma, Fumiaki Sato, Taiki Sekii, Hideo Saito · 6 de abril de 2026

  Learning methods using synthetic data have attracted attention as an effective approach for increasing the diversity of training data while reducing collection costs, thereby improving the robustness of model discrimination. However, many existing methods improve robustness only indirectly through t…

• From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation

  Han Song, Yucheng Zhou, Jianbing Shen, Yu Cheng · 6 de abril de 2026

  Combining Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation, yet the underlying interaction between CoT's exploration and RL's optimization remains unclear. We present a systematic entropy-based analysis that yields three key insights: (1) CoT expands th…

• SEDGE: Structural Extrapolated Data Generation

  Kun Zhang, Jiaqi Sun, Yiqing Li, Ignavier Ng, Namrata Deka, Shaoan Xie · 6 de abril de 2026

  This paper proposes a framework for Structural Extrapolated Data GEneration (SEDGE) based on suitable assumptions on the underlying data generating process. We provide conditions under which data satisfying new specifications can be generated reliably, together with the approximate identifiability o…

• Finding Belief Geometries with Sparse Autoencoders

  Matthew Levinson · 6 de abril de 2026

  Understanding the geometric structure of internal representations is a central goal of mechanistic interpretability. Prior work has shown that transformers trained on sequences generated by hidden Markov models encode probabilistic belief states as simplex-shaped geometries in their residual stream,…