paper-with-me

홈 › Papers

On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models

2022-05-08 · Vedant Singh, Surgan Jandial, Ayush Chopra, Siddharth Ramesh, Balaji Krishnamurthy, Vineeth N. Balasubramanian

Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation. This continues to be a significant area of interest with the rise of new state-of-the-art methods that are based on diffusion models. However, diffusion models provide very little control over the generated image, which led to subsequent works exploring techniques like classifier guidance, that provides a way to trade off diversity with fidelity. In this work, we explore techniques to condition diffusion models with carefully crafted input noise artifacts. This allows generation of images conditioned on semantic attributes. This is different from existing approaches that input Gaussian noise and further introduce conditioning at the diffusion model's inference step. Our experiments over several examples and conditional settings show the potential of our approach.

📄 PDF Abstract BibTeX arXiv:2205.03859

Code (0)

등록된 구현이 없습니다.

Tasks

Conditional Image GenerationDiversityImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Self-supervision via Controlled Transformation and Unpaired Self-conditioning for Low-light Image Enhancement

2025-03-01 · Aupendu Kar, Sobhan K. Dhara, Debashis Sen, Prabir K. Biswas

Real-world low-light images captured by imaging devices suffer from poor visibility and require a domain-specific enhancement to produce artifact-free outputs that reveal details. In this paper, we propose an unpaired lo…

DenoisingImage EnhancementLow-Light Image Enhancement

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space

2026-06-12 · Xichen Pan, Aashu Singh, Satya Narayan Shukla, Xiangjun Fan 외 arxiv

Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative backbones. The emergence of representat…

Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation

2025-12-18 · Min-Jung Kim, Jeongho Kim, Hoiyeong Jin, Junha Hyung 외 arxiv

Recent progress in video diffusion models has spurred growing interest in camera-controlled novel-view video generation for dynamic scenes, aiming to provide creators with cinematic camera control capabilities in post-pr…

Data AugmentationDepth EstimationVideo Generation

DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching

2024-11-26 · CVPR 2025 1 · Emanuele Aiello, Umberto Michieli, Diego Valsesia, Mete Ozay 외

Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts. Existing methods face challenges …

Image GenerationPersonalized Image Generation

Distribution Conditional Denoising: A Flexible Discriminative Image Denoiser

2020-11-24 · Anthony Kelly

A flexible discriminative image denoiser is introduced in which multi-task learning methods are applied to a densoising FCN based on U-Net. The activations of the U-Net model are modified by affine transforms that are a …

DenoisingMulti-Task Learning