Saved in:
Bibliographic Details
Main Authors: George, Franky, Khalid, Muhammad, Khan, Adil
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.16406
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914571169562624
author George, Franky
Khalid, Muhammad
Khan, Adil
author_facet George, Franky
Khalid, Muhammad
Khan, Adil
contents Night-time pedestrian detection remains challenging because labelled night-time data are limited and large illumination differences make daytime-only trained detectors unreliable. Latent diffusion models (LDMs) provide a powerful basis for image-to-image translation and cross-domain augmentation, but their effectiveness in safety-critical perception depends on whether detector-relevant objects and local semantic structure are preserved when translating between source and target domains. In this work, we present Contrastive-SDXL, a day-to-night augmentation framework for night-time pedestrian detection built on SDXL-Turbo and fine-tuned using Low-Rank Adaptation (LoRA). To preserve semantic correspondence between daytime inputs and translated night-time images, we introduce a patch-wise semantic contrastive loss guided by a pretrained DINOv2 encoder rather than generator encoder features. Multi-level DINOv2 self-attention maps enforce both local and global semantic consistency, while an object consistency loss explicitly encourages pedestrian preservation. Contrastive-SDXL produces realistic night-time images, achieving a Frechet Inception Distance (FID) of 22.5. Detectors trained with our synthetic images obtain a 6-7% reduction in miss rate compared with a daytime-only baseline, approaching the performance of detectors trained on real night-time data. These results demonstrate that consistency-driven diffusion augmentation can effectively support safety-critical night-time pedestrian detection.Specific
format Preprint
id arxiv_https___arxiv_org_abs_2605_16406
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Contrastive-SDXL: Annotation-Preserving Night-Time Augmentation for Pedestrian Detection
George, Franky
Khalid, Muhammad
Khan, Adil
Computer Vision and Pattern Recognition
Night-time pedestrian detection remains challenging because labelled night-time data are limited and large illumination differences make daytime-only trained detectors unreliable. Latent diffusion models (LDMs) provide a powerful basis for image-to-image translation and cross-domain augmentation, but their effectiveness in safety-critical perception depends on whether detector-relevant objects and local semantic structure are preserved when translating between source and target domains. In this work, we present Contrastive-SDXL, a day-to-night augmentation framework for night-time pedestrian detection built on SDXL-Turbo and fine-tuned using Low-Rank Adaptation (LoRA). To preserve semantic correspondence between daytime inputs and translated night-time images, we introduce a patch-wise semantic contrastive loss guided by a pretrained DINOv2 encoder rather than generator encoder features. Multi-level DINOv2 self-attention maps enforce both local and global semantic consistency, while an object consistency loss explicitly encourages pedestrian preservation. Contrastive-SDXL produces realistic night-time images, achieving a Frechet Inception Distance (FID) of 22.5. Detectors trained with our synthetic images obtain a 6-7% reduction in miss rate compared with a daytime-only baseline, approaching the performance of detectors trained on real night-time data. These results demonstrate that consistency-driven diffusion augmentation can effectively support safety-critical night-time pedestrian detection.Specific
title Contrastive-SDXL: Annotation-Preserving Night-Time Augmentation for Pedestrian Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.16406