# Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images

arXiv: https://arxiv.org/abs/2412.17109 · HTML: https://mlsanity.com/paper/2412.17109/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 22 Dec 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023)
- [Perceptual Artifacts Localization for Image Synthesis Tasks](https://mlsanity.com/paper/2310.05590/) (2023)
- [ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories](https://mlsanity.com/paper/2302.02373/) (2023)

## Built on by (most cited first, 2 of 2)

- [Synthesizing Artifact Dataset for Pixel-level Detection](https://mlsanity.com/paper/2509.19589/) (2025)
- [AniPrO: Interpretable Anime Image Provenance Detection via Multi-Dimensional Semantic Reasoning](https://mlsanity.com/paper/2609.23345/) (2026)

## Abstract (arXiv)

Artifact detection algorithms are crucial to correcting the output generated by diffusion models. However, because of the variety of artifact forms, existing methods require substantial annotated data for training. This requirement limits their scalability and efficiency, which restricts their wide application. This paper shows that the similarity of denoised images between consecutive time steps during the sampling process is related to the severity of artifacts in images generated by diffusion models. Building on this observation, we introduce the concept of Similarity Trajectory to characterize the sampling process and its correlation with the image artifacts presented. Using an annotated data set of 680 images, which is only 0.1% of the amount of data used in the prior work, we trained a classifier on these trajectories to predict the presence of artifacts in images. By performing 10-fold validation testing on the balanced annotated data set, the classifier can achieve an accuracy of 72.35%, highlighting the connection between the Similarity Trajectory and the occurrence of artifacts. This approach enables differentiation between artifact-exhibiting and natural-looking images using limited training data.