# R4D: Utilizing Reference Objects for Long-Range Distance Estimation

arXiv: https://arxiv.org/abs/2206.04831 · HTML: https://mlsanity.com/paper/2206.04831/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 10 Jun 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Exploring Visual Relationship for Image Captioning](https://mlsanity.com/paper/1809.07041/) (2018)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/1910.06528/) (2019)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships](https://mlsanity.com/paper/2003.00504/) (2020)
- [RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving](https://mlsanity.com/paper/2001.03343/) (2020)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers](https://mlsanity.com/paper/1809.03576/) (2018)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [Shape-Texture Debiased Neural Network Training](https://mlsanity.com/paper/2010.05981/) (2020)
- [Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar](https://mlsanity.com/paper/1912.06613/) (2019)
- [Guided Stereo Matching](https://mlsanity.com/paper/1905.10107/) (2019)
- [Learning Object-specific Distance from a Monocular Image](https://mlsanity.com/paper/1909.04182/) (2019)
- [Depth Sensing Beyond LiDAR Range](https://mlsanity.com/paper/2004.03048/) (2020)
- [End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera](https://mlsanity.com/paper/2006.04082/) (2020)

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

- [Improving Distant 3D Object Detection Using 2D Box Supervision](https://mlsanity.com/paper/2403.09230/) (2024)
- [Monocular Per-Object Distance Estimation with Masked Object Modeling](https://mlsanity.com/paper/2401.03191/) (2024)
- [SimPB++: Simultaneously Detecting 2D and 3D Objects from Multiple Cameras](https://mlsanity.com/paper/2605.01924/) (2026)

## Abstract (arXiv)

Estimating the distance of objects is a safety-critical task for autonomous driving. Focusing on short-range objects, existing methods and datasets neglect the equally important long-range objects. In this paper, we introduce a challenging and under-explored task, which we refer to as Long-Range Distance Estimation, as well as two datasets to validate new methods developed for this task. We then proposeR4D, the first framework to accurately estimate the distance of long-range objects by using references with known distances in the scene. Drawing inspiration from human perception, R4D builds a graph by connecting a target object to all references. An edge in the graph encodes the relative distance information between a pair of target and reference objects. An attention module is then used to weigh the importance of reference objects and combine them into one target object distance prediction. Experiments on the two proposed datasets demonstrate the effectiveness and robustness of R4D by showing significant improvements compared to existing baselines. We are looking to make the proposed dataset, Waymo OpenDataset - Long-Range Labels, available publicly at waymo.com/open/download.