# Objects as Spatio-Temporal 2.5D points

arXiv: https://arxiv.org/abs/2212.02755 · HTML: https://mlsanity.com/paper/2212.02755/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 46 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [Learning Depth from Monocular Videos using Direct Methods](https://mlsanity.com/paper/1712.00175/) (2017)
- [Bounding Box Regression with Uncertainty for Accurate Object Detection](https://mlsanity.com/paper/1809.08545/) (2018)
- [Receptive Field Block Net for Accurate and Fast Object Detection](https://mlsanity.com/paper/1711.07767/) (2017)
- [Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud](https://mlsanity.com/paper/1903.09847/) (2019)

## Abstract (arXiv)

Determining accurate bird's eye view (BEV) positions of objects and tracks in a scene is vital for various perception tasks including object interactions mapping, scenario extraction etc., however, the level of supervision required to accomplish that is extremely challenging to procure. We propose a light-weight, weakly supervised method to estimate 3D position of objects by jointly learning to regress the 2D object detections and scene's depth prediction in a single feed-forward pass of a network. Our proposed method extends a center-point based single-shot object detector, and introduces a novel object representation where each object is modeled as a BEV point spatio-temporally, without the need of any 3D or BEV annotations for training and LiDAR data at query time. The approach leverages readily available 2D object supervision along with LiDAR point clouds (used only during training) to jointly train a single network, that learns to predict 2D object detection alongside the whole scene's depth, to spatio-temporally model object tracks as points in BEV. The proposed method is computationally over ~10x efficient compared to recent SOTA approaches while achieving comparable accuracies on KITTI tracking benchmark.