# Addressing Diverging Training Costs using BEVRestore for High-resolution Bird's Eye View Map Construction

arXiv: https://arxiv.org/abs/2405.01016 · HTML: https://mlsanity.com/paper/2405.01016/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [HDMapNet: An Online HD Map Construction and Evaluation Framework](https://mlsanity.com/paper/2107.06307/) (2021)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [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)
- [Multimodal Virtual Point 3D Detection](https://mlsanity.com/paper/2111.06881/) (2021)
- [CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception](https://mlsanity.com/paper/2304.00670/) (2023)
- [End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve](https://mlsanity.com/paper/2306.09700/) (2023)
- [UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation](https://mlsanity.com/paper/2308.07732/) (2023)
- [FISHING Net: Future Inference of Semantic Heatmaps In Grids](https://mlsanity.com/paper/2006.09917/) (2020)
- [InstaGraM: Instance-level Graph Modeling for Vectorized HD Map Learning](https://mlsanity.com/paper/2301.04470/) (2023)
- [X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation](https://mlsanity.com/paper/2210.06778/) (2022)
- [MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models](https://mlsanity.com/paper/2308.12963/) (2023)
- [LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation](https://mlsanity.com/paper/2304.11379/) (2023)
- [MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction](https://mlsanity.com/paper/2306.10301/) (2023)
- [Is the deconvolution layer the same as a convolutional layer?](https://mlsanity.com/paper/1609.07009/) (2016)
- [MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation](https://mlsanity.com/paper/2304.09801/) (2023)
- [BroadBEV: Collaborative LiDAR-camera Fusion for Broad-sighted Bird's Eye View Map Construction](https://mlsanity.com/paper/2309.11119/) (2023)
- [BEVSeg2TP: Surround View Camera Bird's-Eye-View Based Joint Vehicle Segmentation and Ego Vehicle Trajectory Prediction](https://mlsanity.com/paper/2312.13081/) (2023)

## Abstract (arXiv)

Recent advancements in Bird's Eye View (BEV) fusion for map construction have demonstrated remarkable mapping of urban environments. However, their deep and bulky architecture incurs substantial amounts of backpropagation memory and computing latency. Consequently, the problem poses an unavoidable bottleneck in constructing high-resolution (HR) BEV maps, as their large-sized features cause significant increases in costs including GPU memory consumption and computing latency, named diverging training costs issue. Affected by the problem, most existing methods adopt low-resolution (LR) BEV and struggle to estimate the precise locations of urban scene components like road lanes, and sidewalks. As the imprecision leads to risky motion planning like collision avoidance, the diverging training costs issue has to be resolved. In this paper, we address the issue with our novel BEVRestore mechanism. Specifically, our proposed model encodes the features of each sensor to LR BEV space and restores them to HR space to establish a memory-efficient map constructor. To this end, we introduce the BEV restoration strategy, which restores aliasing, and blocky artifacts of the up-scaled BEV features, and narrows down the width of the labels. Our extensive experiments show that the proposed mechanism provides a plug-and-play, memory-efficient pipeline, enabling an HR map construction with a broad BEV scope.