# STS: Surround-view Temporal Stereo for Multi-view 3D Detection

arXiv: https://arxiv.org/abs/2208.10145 · HTML: https://mlsanity.com/paper/2208.10145/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 38 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 30 of 34)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [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)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [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)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [How do neural networks see depth in single images?](https://mlsanity.com/paper/1905.07005/) (2019)
- [Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation](https://mlsanity.com/paper/2201.01501/) (2022)
- [AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network](https://mlsanity.com/paper/2108.03824/) (2021)
- [Multi-Frame Self-Supervised Depth with Transformers](https://mlsanity.com/paper/2204.07616/) (2022)
- [Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume](https://mlsanity.com/paper/1912.11746/) (2019)
- [MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera](https://mlsanity.com/paper/2011.11814/) (2020)

## Built on by (most cited first, 30 of 53)

- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection](https://mlsanity.com/paper/2210.02443/) (2022)
- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [FB-BEV: BEV Representation from Forward-Backward View Transformations](https://mlsanity.com/paper/2308.02236/) (2023)
- [DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving](https://mlsanity.com/paper/2405.04390/) (2024)
- [BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deployment](https://mlsanity.com/paper/2211.17111/) (2022)
- [BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection](https://mlsanity.com/paper/2303.08498/) (2023)
- [Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception](https://mlsanity.com/paper/2303.05970/) (2023)
- [Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction](https://mlsanity.com/paper/2304.00967/) (2023)
- [UniWorld: Autonomous Driving Pre-training via World Models](https://mlsanity.com/paper/2308.07234/) (2023)
- [BEVHeight++: Toward Robust Visual Centric 3D Object Detection](https://mlsanity.com/paper/2309.16179/) (2023)
- [MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception](https://mlsanity.com/paper/2211.10593/) (2022)
- [X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2303.02203/) (2023)
- [Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark](https://mlsanity.com/paper/2212.08914/) (2022)
- [Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2303.01212/) (2023)
- [Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion](https://mlsanity.com/paper/2307.16532/) (2023)
- [FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection](https://mlsanity.com/paper/2301.04467/) (2023)
- [BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks](https://mlsanity.com/paper/2212.01231/) (2022)
- [CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection](https://mlsanity.com/paper/2411.03013/) (2024)
- [MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2402.11677/) (2024)
- [OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks](https://mlsanity.com/paper/2404.14027/) (2024)
- [HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras](https://mlsanity.com/paper/2404.02517/) (2024)
- [3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers](https://mlsanity.com/paper/2211.14710/) (2022)
- [UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving](https://mlsanity.com/paper/2305.18829/) (2023)
- [Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection](https://mlsanity.com/paper/2310.15670/) (2023)
- [SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects](https://mlsanity.com/paper/2403.20318/) (2024)
- [GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection](https://mlsanity.com/paper/2409.01816/) (2024)
- [SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection](https://mlsanity.com/paper/2303.16818/) (2023)
- [Geometric-aware Pretraining for Vision-centric 3D Object Detection](https://mlsanity.com/paper/2304.03105/) (2023)
- [3D Video Object Detection with Learnable Object-Centric Global Optimization](https://mlsanity.com/paper/2303.15416/) (2023)

## Abstract (arXiv)

Learning accurate depth is essential to multi-view 3D object detection. Recent approaches mainly learn depth from monocular images, which confront inherent difficulties due to the ill-posed nature of monocular depth learning. Instead of using a sole monocular depth method, in this work, we propose a novel Surround-view Temporal Stereo (STS) technique that leverages the geometry correspondence between frames across time to facilitate accurate depth learning. Specifically, we regard the field of views from all cameras around the ego vehicle as a unified view, namely surroundview, and conduct temporal stereo matching on it. The resulting geometrical correspondence between different frames from STS is utilized and combined with the monocular depth to yield final depth prediction. Comprehensive experiments on nuScenes show that STS greatly boosts 3D detection ability, notably for medium and long distance objects. On BEVDepth with ResNet-50 backbone, STS improves mAP and NDS by 2.6% and 1.4%, respectively. Consistent improvements are observed when using a larger backbone and a larger image resolution, demonstrating its effectiveness