# Input Resolution Matters: Real-Time Object Detection Latency

arXiv: https://arxiv.org/abs/2609.12920 · HTML: https://mlsanity.com/paper/2609.12920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences](https://mlsanity.com/paper/2310.04621/) (2023)
- [ESOD: Efficient Small Object Detection on High-Resolution Images](https://mlsanity.com/paper/2407.16424/) (2024)
- [One Size Does Not Fit All: Quantifying and Exposing the Accuracy-Latency Trade-off in Machine Learning Cloud Service APIs via Tolerance Tiers](https://mlsanity.com/paper/1906.11307/) (2019)
- [YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems](https://mlsanity.com/paper/2307.13901/) (2023)
- [A Study of Image Pre-processing for Faster Object Recognition](https://mlsanity.com/paper/2011.06928/) (2020)
- [CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection](https://mlsanity.com/paper/2505.23317/) (2025)

## Abstract (arXiv)

We model total latency as the convolution of preprocessing, inference, and postprocessing distributions under a simplifying independence approximation, with selected stage parameters expressed as functions of source-image resolution. Under this assumption, the probability density of the total latency is the convolution of the stage-wise densities, and its cumulative distribution function (CDF) provides the distribution of end-to-end detection time. Each stage is modeled by a parametric distribution (e.g., Exponential, Erlang, Normal, Gamma), with parameters expressed as functions of the source-image resolution. Experiments with YOLOv11n on NVIDIA Jetson Orin NX using COCO2017 images across multiple resolutions assess the proposed models against fixed-parameter baselines using Kolmogorov Smirnov, Anderson Darling, and Cram'er von Mises statistics. The results indicate that resolution-aware parameterization can improve distributional approximation in the measured setting, particularly for the more flexible Normal and Gamma models, while the quality of fit remains distribution dependent. Our contribution is a theoretically grounded and lightweight formulation for studying resolution-dependent latency distributions in a measured object detection pipeline.