# SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects

arXiv: https://arxiv.org/abs/2403.20318 · HTML: https://mlsanity.com/paper/2403.20318/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 87 of its 113 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 30 of 87)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [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)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [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)
- [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)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [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)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [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)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)

## Built on by (most cited first, 12 of 12)

- [Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection](https://mlsanity.com/paper/2505.04594/) (2025)
- [RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection](https://mlsanity.com/paper/2504.09086/) (2025)
- [AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction](https://mlsanity.com/paper/2503.13430/) (2025)
- [CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector](https://mlsanity.com/paper/2508.11185/) (2025)
- [UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos](https://mlsanity.com/paper/2510.15018/) (2025)
- [RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry](https://mlsanity.com/paper/2407.19154/) (2024)
- [Towards Intrinsic-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2603.27059/) (2026)
- [ParCon: Noise-Robust Collaborative Perception via Multi-module Parallel Connection](https://mlsanity.com/paper/2407.11546/) (2024)
- [AdaOcc: Adaptive-Resolution Occupancy Prediction](https://mlsanity.com/paper/2408.13454/) (2024)
- [OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2506.23565/) (2025)
- [StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception](https://mlsanity.com/paper/2507.06687/) (2025)
- [A Controlled Evaluation of Model Rankings and Input Reliance in Surface Water Segmentation](https://mlsanity.com/paper/2608.30895/) (2026)

## Abstract (arXiv)

Monocular 3D detectors achieve remarkable performance on cars and smaller objects. However, their performance drops on larger objects, leading to fatal accidents. Some attribute the failures to training data scarcity or their receptive field requirements of large objects. In this paper, we highlight this understudied problem of generalization to large objects. We find that modern frontal detectors struggle to generalize to large objects even on nearly balanced datasets. We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects. To bridge this gap, we comprehensively investigate regression and dice losses, examining their robustness under varying error levels and object sizes. We mathematically prove that the dice loss leads to superior noise-robustness and model convergence for large objects compared to regression losses for a simplified case. Leveraging our theoretical insights, we propose SeaBird (Segmentation in Bird's View) as the first step towards generalizing to large objects. SeaBird effectively integrates BEV segmentation on foreground objects for 3D detection, with the segmentation head trained with the dice loss. SeaBird achieves SoTA results on the KITTI-360 leaderboard and improves existing detectors on the nuScenes leaderboard, particularly for large objects. Code and models at https://github.com/abhi1kumar/SeaBird