# Burst Imaging for Light-Constrained Structure-From-Motion

arXiv: https://arxiv.org/abs/2108.09895 · HTML: https://mlsanity.com/paper/2108.09895/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 23 Aug 2021.

## Builds on (most cited first, 16 of 16)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://mlsanity.com/paper/1906.06543/) (2019)
- [Handheld Multi-Frame Super-Resolution](https://mlsanity.com/paper/1905.03277/) (2019)
- [Cascaded Deep Video Deblurring Using Temporal Sharpness Prior](https://mlsanity.com/paper/2004.02501/) (2020)
- [Deep Burst Super-Resolution](https://mlsanity.com/paper/2101.10997/) (2021)
- [Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes](https://mlsanity.com/paper/2003.14013/) (2020)
- [Handheld Mobile Photography in Very Low Light](https://mlsanity.com/paper/1910.11336/) (2019)
- [Quanta Burst Photography](https://mlsanity.com/paper/2006.11840/) (2020)
- [LiFF: Light Field Features in Scale and Depth](https://mlsanity.com/paper/1901.03916/) (2019)
- [Classification Driven Dynamic Image Enhancement](https://mlsanity.com/paper/1710.07558/) (2017)

## Built on by (most cited first, 3 of 3)

- [Dark3R: Learning Structure from Motion in the Dark](https://mlsanity.com/paper/2603.05330/) (2026)
- [BuFF: Burst Feature Finder for Light-Constrained 3D Reconstruction](https://mlsanity.com/paper/2209.09470/) (2022)
- [LBurst: Learning-Based Robotic Burst Feature Extraction for 3D Reconstruction in Low Light](https://mlsanity.com/paper/2410.23522/) (2024)

## Abstract (arXiv)

Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this paper we develop an image processing technique for aiding 3D reconstruction from images acquired in low light conditions. Our technique, based on burst photography, uses direct methods for image registration within bursts of short exposure time images to improve the robustness and accuracy of feature-based structure-from-motion (SfM). We demonstrate improved SfM performance in challenging light-constrained scenes, including quantitative evaluations that show improved feature performance and camera pose estimates. Additionally, we show that our method converges more frequently to correct reconstructions than the state-of-the-art. Our method is a significant step towards allowing robots to operate in low light conditions, with potential applications to robots operating in environments such as underground mines and night time operation.