# Learning Ego 3D Representation as Ray Tracing

arXiv: https://arxiv.org/abs/2206.04042 · HTML: https://mlsanity.com/paper/2206.04042/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 44 references that are in the map.
- First posted on arXiv 8 Jun 2022.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks](https://mlsanity.com/paper/2003.13402/) (2020)

## Built on by (most cited first, 30 of 43)

- [PolarFormer: Multi-camera 3D Object Detection with Polar Transformer](https://mlsanity.com/paper/2206.15398/) (2022)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [DeepInteraction: 3D Object Detection via Modality Interaction](https://mlsanity.com/paper/2208.11112/) (2022)
- [PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation](https://mlsanity.com/paper/2306.10013/) (2023)
- [CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception](https://mlsanity.com/paper/2304.00670/) (2023)
- [UniPAD: A Universal Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2310.08370/) (2023)
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022)
- [PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm](https://mlsanity.com/paper/2310.08586/) (2023)
- [Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction](https://mlsanity.com/paper/2303.08815/) (2023)
- [Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction](https://mlsanity.com/paper/2304.00967/) (2023)
- [Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline](https://mlsanity.com/paper/2301.12511/) (2023)
- [LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection](https://mlsanity.com/paper/2206.07705/) (2022)
- [RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation](https://mlsanity.com/paper/2312.11829/) (2023)
- [RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detection](https://mlsanity.com/paper/2307.10249/) (2023)
- [Grounded Affordance from Exocentric View](https://mlsanity.com/paper/2208.13196/) (2022)
- [FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection](https://mlsanity.com/paper/2301.04467/) (2023)
- [Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2212.05505/) (2022)
- [HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View](https://mlsanity.com/paper/2307.13510/) (2023)
- [Fast-BEV: Towards Real-time On-vehicle Bird's-Eye View Perception](https://mlsanity.com/paper/2301.07870/) (2023)
- [A Simple Baseline for Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2208.10035/) (2022)
- [3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers](https://mlsanity.com/paper/2211.14710/) (2022)
- [DeepInteraction++: Multi-Modality Interaction for Autonomous Driving](https://mlsanity.com/paper/2408.05075/) (2024)
- [VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2411.14716/) (2024)
- [Improving Bird's Eye View Semantic Segmentation by Task Decomposition](https://mlsanity.com/paper/2404.01925/) (2024)
- [F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Driving](https://mlsanity.com/paper/2303.03651/) (2023)
- [DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.16628/) (2023)
- [VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene](https://mlsanity.com/paper/2304.09807/) (2023)
- [Eliminating Cross-modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection](https://mlsanity.com/paper/2403.07372/) (2024)
- [SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection](https://mlsanity.com/paper/2308.13794/) (2023)
- [LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement](https://mlsanity.com/paper/2401.17609/) (2024)

## Abstract (arXiv)

A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird's-eye-view (BEV) coordinate frame of the ego car in order to ground downstream planner. Existing perception methods often rely on error-prone depth estimation of the whole scene or learning sparse virtual 3D representations without the target geometry structure, both of which remain limited in performance and/or capability. In this paper, we present a novel end-to-end architecture for ego 3D representation learning from an arbitrary number of unconstrained camera views. Inspired by the ray tracing principle, we design a polarized grid of "imaginary eyes" as the learnable ego 3D representation and formulate the learning process with the adaptive attention mechanism in conjunction with the 3D-to-2D projection. Critically, this formulation allows extracting rich 3D representation from 2D images without any depth supervision, and with the built-in geometry structure consistent w.r.t. BEV. Despite its simplicity and versatility, extensive experiments on standard BEV visual tasks (e.g., camera-based 3D object detection and BEV segmentation) show that our model outperforms all state-of-the-art alternatives significantly, with an extra advantage in computational efficiency from multi-task learning.