paper-with-me

Papers Conditional Image Generation

“Conditional Image Generation” 태그가 달린 논문 327편 · 필터 해제

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

2026-08-19 · Libo Chen, Souvik Ghosh, Teo Deveney, Chris Budd 외 arxiv

We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at infere…

Conditional Image Generation

Energy-Guided Flow Matching

2026-08-06 · Haoyang Tong, Yu He, Fang Li, Lichen Ma 외 arxiv

Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a f…

Conditional Image GenerationText-to-Image Generation

Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

2026-07-23 · Rogerio Guimaraes, Pietro Perona arxiv

Diffusion and flow-matching models dominate conditional image generation, yet inference-time scaling for these models is far less developed than for autoregressive language models. Because final quality is highly sensiti…

Conditional Image Generation

DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models

2026-07-04 · Chunnan Shang, Xin Zhang, Zhizhong Wang, Hongwei Wang arxiv

Diffusion models have become a dominant paradigm for conditional image generation, yet existing approaches generally follow two directions: task-specific designs that can improve performance but limit generalization, and…

Conditional Image GenerationImage Super-ResolutionImage DeblurringStyle Transfer

Shift-and-Sum Quantization for Visual Autoregressive Models

2026-06-15 · Jaehyeon Moon, Bumsub Ham arxiv

Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive models (VAR), however, remains relatively unexplored. We identify two key…

Conditional Image Generation

Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

2026-06-08 · Abhi Gupta, Polina Barabanshchikova, Vikas Garg, Samuel Kaski 외 arxiv

The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divi…

Conditional Image Generation

Compositional Generative Modeling from Decentralized Data

2026-06-08 · Mashrur M. Morshed, Vishnu Naresh Boddeti arxiv

Learning the compositional nature of the physical world requires joint observation of interacting factors. However, because practical data is often decentralized, these factors are fragmented across isolated silos. Exist…

Conditional Image GenerationFederated Learning

CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors

2026-06-04 · Shengxi Li, Zhaokun Hu, Ce Zheng, Mai Xu 외 arxiv

Unsupervised conditional image generation (UCGen) aims to control generation without relying on manually annotated labels, yet remains challenging due to unstructured semantic representations across granularities. To add…

Conditional Image Generation

VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation

2026-05-28 · Xinyao Liao, Qiyuan He, Yicong Li, Jiayin Zhu 외 arxiv

Autoregressive image and video generators are trained with teacher-forced histories but must sample from their own generated prefixes at inference time, making them vulnerable to exposure bias and prefix drift. Existing …

Conditional Image GenerationText-to-Video GenerationText-to-Image Generation

Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models

2026-05-22 · Egor Lifar, Semyon Savkin, Timur Garipov, Shangyuan Tong 외 arxiv

In this paper, we propose Diffusion Domain Expansion (DDE), a method that efficiently extends pre-trained diffusion models to generate larger objects and handle more complex conditioning beyond their original capabilitie…

Conditional Image Generation

AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation

2026-05-10 · Shogo Noguchi arxiv

Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human poses, segmentation maps, and depth. By applying these techniques to im…

Conditional Image GenerationSemantic SegmentationImage AugmentationData Augmentation

Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation

2026-05-01 · Nadav Z. Cohen, Ofir Abramovich, Ariel Shamir arxiv

Text-to-image diffusion models generate images by gradually converting white Gaussian noise into a natural image. White Gaussian noise is well suited for producing diverse outputs from a single text prompt due to its abs…

Conditional Image Generation

TokenLight: Precise Lighting Control in Images using Attribute Tokens

2026-04-16 · Sumit Chaturvedi, Yannick Hold-Geoffroy, Mengwei Ren, Jingyuan Liu 외 arxiv

This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and intr…

Conditional Image GenerationContinuous ControlInverse RenderingImage Relighting

Generative Refinement Networks for Visual Synthesis

2026-04-14 · Jian Han, Jinlai Liu, Jiahuan Wang, Bingyue Peng 외 arxiv

While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models ar…

Conditional Image GenerationText-to-Video GenerationImage Reconstruction

PHAC: Promptable Human Amodal Completion

2026-03-16 · Seung Young Noh, Ju Yong Chang arxiv

Conditional image generation methods are increasingly used in human-centric applications, yet existing human amodal completion (HAC) models offer users limited control over the completed content. Given an occluded person…

Conditional Image Generation

Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with glioma

2026-03-09 · Selena Huisman, Nordin Belkacemi, Vera C. Keil, Joost Verhoeff 외 arxiv

Brain tumors result in 20 years of lost life on average. Standard therapies induce complex structural changes in the brain that are monitored through MRI. Recent developments in artificial intelligence (AI) enable condit…

Conditional Image Generation

DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis

2026-02-26 · Xinglong Luo, Ao Luo, Zhengning Wang, Yueqi Yang 외 arxiv

Image alignment is a fundamental task in computer vision with broad applications. Existing methods predominantly employ optical flow-based image warping. However, this technique is susceptible to common challenges such a…

Conditional Image Generation

CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation

2026-02-25 · YuXin Song, Yu Lu, Haoyuan Sun, Huanjin Yao 외 arxiv

Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for semantic synthesis, while others rely o…

Conditional Image Generation

Efficient Text-Guided Convolutional Adapter for the Diffusion Model

2026-02-16 · Aryan Das, Koushik Biswas, Swalpa Kumar Roy, Badri Narayana Patro 외 arxiv

We introduce the Nexus Adapters, novel text-guided efficient adapters to the diffusion-based framework for the Structure Preserving Conditional Generation (SPCG). Recently, structure-preserving methods have achieved prom…

Conditional Image Generation

Ambient Dataloops: Generative Models for Dataset Refinement

2026-01-21 · Adrián Rodríguez-Muñoz, William Daspit, Adam Klivans, Antonio Torralba 외 arxiv

We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets contain samples of highly varying quality, a…

Conditional Image GenerationProtein Design
1–20 / 327 다음 →