Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light

• URL: http://arxiv.org/abs/2605.22455v1
• Date: Thu, 21 May 2026 13:20:11 GMT
• Title: Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light
• Abstract summary: We show how synthetic low-light samples can be used to better characterize the performance of a state-of-the-art object detection model.<n>We use a synthetic RAW image augmentation technique to generate low-light samples that match the noise model of the camera sensor.<n>Performance metrics on real and synthetic low-light data are similar, indicating that the AI model finds it hard to distinguish between them.
• Score: 2.0651472773361976
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Real-world deployment of AI vision models is both fueled and limited by the data available for training and testing. Real datasets are sparse and uneven: long-tailed or unbalanced distributions hinder generalization, and the low number of samples in low density regions makes it hard to run evaluations. Synthetic data can fill these gaps, providing us with a way to sample the input space more continuously and improve data coverage for benchmarks. Focusing on the autonomous driving safety-critical case of pedestrian detection in the dark, we show how synthetic low-light samples can be used to better characterize the performance of a state-of-the-art object detection model as a function of the scene illumination. We use a synthetic RAW image augmentation technique to generate low-light samples that match the noise model of the camera sensor. Performance metrics on real and synthetic low-light data are similar, indicating that the AI model finds it hard to distinguish between them.

Related papers

• Training with synthetic data for drone detection in thermal imagery [0.9236074230806578]
  Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging.<n>This work investigates a synthetic-first training strategy that combines synthetic scene generation with fine-tuning on real data.
  arXiv  Detail & Related papers  (2026-08-18T13:59:58Z)
• Explaining raw data complexity to improve satellite onboard processing [0.815557531820863]
  This study investigates the effects of utilising raw data on deep learning models for object detection and classification tasks.<n>Two object detection models (YOLOv11n and YOLOX-S) are trained on both raw and L1 datasets.<n>Results indicate that while both models perform similarly at low to medium confidence thresholds, the model trained on raw data struggles with object boundary identification at high confidence levels.
  arXiv  Detail & Related papers  (2025-10-08T10:26:02Z)
• LuxDiT: Lighting Estimation with Video Diffusion Transformer [66.60450792095901]
  Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics.<n>We propose LuxDiT, a novel data-driven approach that fine-tunes a video diffusion transformer to generate HDR environment maps conditioned on visual input.
  arXiv  Detail & Related papers  (2025-09-03T19:59:20Z)
• AI-Generated Fall Data: Assessing LLMs and Diffusion Model for Wearable Fall Detection [3.5912245880418125]
  Training fall detection systems is challenging due to the scarcity of real-world fall data, particularly from elderly individuals.<n>This study evaluates text-to-motion and text-to-text models in simulating realistic fall scenarios.<n>We generate synthetic datasets and integrate them with four real-world baseline datasets to assess their impact on fall detection performance.
  arXiv  Detail & Related papers  (2025-05-07T02:30:33Z)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models.<n>In this paper, we investigate how detection performance varies across model backbones, types, and datasets.<n>We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• BVI-RLV: A Fully Registered Dataset and Benchmarks for Low-Light Video Enhancement [56.97766265018334]
  This paper introduces a low-light video dataset, consisting of 40 scenes with various motion scenarios under two distinct low-lighting conditions. We provide fully registered ground truth data captured in normal light using a programmable motorized dolly and refine it via an image-based approach for pixel-wise frame alignment across different light levels. Our experimental results demonstrate the significance of fully registered video pairs for low-light video enhancement (LLVE) and the comprehensive evaluation shows that the models trained with our dataset outperform those trained with the existing datasets.
  arXiv  Detail & Related papers  (2024-07-03T22:41:49Z)
• SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection [53.19618419772467]
  Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. With the development of Transformer, the scale of SIRST models is constantly increasing. With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
  arXiv  Detail & Related papers  (2024-03-08T16:14:54Z)
• Instance Segmentation in the Dark [43.85818645776587]
  We take a deep look at instance segmentation in the dark and introduce several techniques that substantially boost the low-light inference accuracy. We propose a novel learning method that relies on an adaptive weighted downsampling layer, a smooth-oriented convolutional block, and disturbance suppression learning. We capture a real-world low-light instance segmentation dataset comprising over two thousand paired low/normal-light images with instance-level pixel-wise annotations.
  arXiv  Detail & Related papers  (2023-04-27T16:02:29Z)
• NeRF in detail: Learning to sample for view synthesis [104.75126790300735]
  Neural radiance fields (NeRF) methods have demonstrated impressive novel view synthesis. In this work we address a clear limitation of the vanilla coarse-to-fine approach -- that it is based on a performance and not trained end-to-end for the task at hand. We introduce a differentiable module that learns to propose samples and their importance for the fine network, and consider and compare multiple alternatives for its neural architecture.
  arXiv  Detail & Related papers  (2021-06-09T17:59:10Z)
• Negative Data Augmentation [127.28042046152954]
  We show that negative data augmentation samples provide information on the support of the data distribution. We introduce a new GAN training objective where we use NDA as an additional source of synthetic data for the discriminator. Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.
  arXiv  Detail & Related papers  (2021-02-09T20:28:35Z)
• Can Synthetic Data Improve Object Detection Results for Remote Sensing Images? [15.466412729455874]
  We propose the use of realistic synthetic data with a wide distribution to improve the performance of remote sensing image aircraft detection. We randomly set the parameters during rendering, such as the size of the instance and the class of background images. In order to make the synthetic images more realistic, we refine the synthetic images at the pixel level using CycleGAN with real unlabeled images.
  arXiv  Detail & Related papers  (2020-06-09T02:23:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.