REVIEW 13 cited by
Palette: Image-to-Image Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and JPEG restoration. Our simple implementation of image-to-image diffusion models outperforms strong GAN and regression baselines on all tasks, without task-specific hyper-parameter tuning, architecture customization, or any auxiliary loss or sophisticated new techniques needed. We uncover the impact of an L2 vs. L1 loss in the denoising diffusion objective on sample diversity, and demonstrate the importance of self-attention in the neural architecture through empirical studies. Importantly, we advocate a unified evaluation protocol based on ImageNet, with human evaluation and sample quality scores (FID, Inception Score, Classification Accuracy of a pre-trained ResNet-50, and Perceptual Distance against original images). We expect this standardized evaluation protocol to play a role in advancing image-to-image translation research. Finally, we show that a generalist, multi-task diffusion model performs as well or better than task-specific specialist counterparts. Check out https://diffusion-palette.github.io for an overview of the results.
Forward citations
Cited by 13 Pith papers
-
Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
DiRIM uses a diffusion model with recurrent score refinement to sample pixel-space joint posteriors of the lensed source and foreground mass map, reproducing mock strong-lens observations to the noise level.
-
Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands
A 5D texture parameterization plus centerline-based canonical space and supervised diffusion enables generation and texture transfer of feature-rich hair strands independent of style.
-
DreamFusion: Text-to-3D using 2D Diffusion
Optimizes a Neural Radiance Field via probability density distillation from a 2D diffusion model to produce text-conditioned 3D scenes viewable from any angle.
-
Diffusion Posterior Sampling for General Noisy Inverse Problems
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
-
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Imagen achieves state-of-the-art photorealistic text-to-image generation by scaling a text-only pretrained T5 language model within a diffusion framework, reaching FID 7.27 on COCO without training on it.
-
Video Diffusion Models
A diffusion model for video generation extends image architectures with joint image-video training and improved conditional sampling, delivering first large-scale text-to-video results and state-of-the-art performance...
-
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
-
SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction
SHFormer, a hybrid spectral-filtering CNN and high-pass-kernel transformer, improves accelerated MRI reconstruction and generalization to unseen contrasts and acceleration factors.
-
Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors
A tiny, invisible perturbation added to a published grayscale image can force AI colorizers to produce content-wrong colors (blue apples), an effect this paper measures and optimizes with a new semantic color-plausibi...
-
AU-IQA: A Benchmark Dataset for Perceptual Quality Assessment of AI-Enhanced User-Generated Content
AU-IQA is a new 4,800-image benchmark showing existing quality models, mainly those trained on ordinary user content, only partially predict human ratings of AI-enhanced photos.
-
SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts
SPADE combines sketch-guided path planning with diffusion-augmented imitation learning to achieve better generalization and lower error with fewer parameters than prior methods.
-
Multimodal Image Colorization: Quantifying the Impact of Text-Conditioned Guidance on Grayscale-to-Color Translation
Text conditioning improves PSNR by ~5.7%, SSIM by ~1.4%, colorfulness by up to 36.6%, and reduces LPIPS by ~9.5% across U-Net and Stable Diffusion colorization models.
-
Pinterest Canvas: Large-Scale Image Generation at Pinterest
A FLUX-style base diffusion model plus task-specific fine-tunes and product-preserving pipelines yields double-digit Pinterest ads engagement lifts and higher no-defect rates than GPT-Image, FLUX Kontext, and Nano Banana.
Discussion (0). Sign in to comment.