Papers › SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of...

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

29 Mar 2024CVPR 2024 1arXiv:2403.20318archive 2025-07-28

Abhinav Kumar, Yuliang Guo, Xinyu Huang, Liu Ren, Xiaoming Liu

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

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

abhi1kumar/seabird officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection (arXiv:2207.10758; that paper's own run record: 9 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Object Detection3D Object Detection From Monocular ImagesAttributeBEV SegmentationSegmentationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection nuScenes Camera Only SeaBird Future Frame false #14 of 19 Archive leaderboard report
3D Object Detection nuScenes Camera Only SeaBird NDS 59.7 #14 of 19 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 SeaBird + PanopticBEV AP25 37.12 #1 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 SeaBird + PanopticBEV AP50 4.64 #1 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 SeaBird + Image2Maps AP25 35.04 #4 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 SeaBird + Image2Maps AP50 3.14 #4 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Dice Loss

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections