Pith. sign in

REVIEW 8 cited by

BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.10092 v2 pith:XUSXZRQX submitted 2022-06-21 cs.CV

Yinhao Li , Zheng Ge , Guanyi Yu , Jinrong Yang , Zengran Wang , Yukang Shi , Jianjian Sun , Zeming Li This is my paper
classification cs.CV
keywords depthbevdepthdetectionestimationobjectcameramoduleachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird's-Eye-View (BEV) 3D object detection. Our work is based on a key observation -- depth estimation in recent approaches is surprisingly inadequate given the fact that depth is essential to camera 3D detection. Our BEVDepth resolves this by leveraging explicit depth supervision. A camera-awareness depth estimation module is also introduced to facilitate the depth predicting capability. Besides, we design a novel Depth Refinement Module to counter the side effects carried by imprecise feature unprojection. Aided by customized Efficient Voxel Pooling and multi-frame mechanism, BEVDepth achieves the new state-of-the-art 60.9% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the NDS score of a camera model reaches 60%.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction

    cs.CV 2026-07 conditional novelty 7.0 of 10

    Factorized Dense Routing approximates unconstrained 2D-to-3D feature mixing by hierarchical tensor contractions, yielding global-context occupancy prediction that remains robust without camera extrinsics.

  2. SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Prediction

    cs.CV 2026-07 accept novelty 6.5 of 10

    SparseOcc++ decouples geometry completion (via orthogonal SCF regression on sparse anchors) from semantics, improving IoU 2.3 points and running 3.9 imes faster than SparseOcc on nuScenes while 5.9 imes faster than Oc...

  3. RayOcc: Occlusion-Aware Ray Occupancy Estimation via Gaussian Mixture Intensity

    cs.CV 2026-07 conditional novelty 6.0 of 10

    RayOcc models each camera ray as a non-normalized Gaussian mixture with Poisson-based occupancy probabilities, allowing multiple depth hypotheses per ray and improving Gaussian-initialized 3D occupancy prediction on nuScenes.

  4. Semantic Causality-Aware Vision-Based 3D Occupancy Prediction

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A class-conditional gradient loss (Causal Loss) plus channel-grouped lifting, learnable camera offsets, and normalized convolution raises Occ3D mIoU by 1.2/0.8 points and cuts the camera-noise mIoU drop from 32% to 7%.

  5. GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    GTAD combines an in-model latent denoising network with global temporal interaction to improve camera-based 3D semantic occupancy prediction, reporting 40.76 mIoU on Occ3D-nuScenes at 12 epochs.

  6. Rethink 3D Object Detection from Physical World

    cs.RO 2025-06 conditional novelty 5.0 of 10

    Latency-aware and planning-aware AP metrics re-rank 3D object detectors for autonomous driving, showing that faster, safer models can beat higher-mAP ones.

  7. SKGE-SWIN: End-To-End Autonomous Vehicle Waypoint Prediction and Navigation Using Skip Stage Swin Transformer

    cs.CV 2025-08 reject novelty 4.0 of 10

    Adding skip connections between Swin Transformer stages raises the CARLA Driving Score of the authors' end-to-end driving model from 29.7 (x13 CNN baseline) to 37.1 on Town05, in a single reported evaluation run.

  8. AWML: An Open-Source ML-based Robotics Perception Framework to Deploy for ROS-based Autonomous Driving Software

    cs.RO 2025-05 conditional novelty 4.0 of 10

    AWML is a new MLOps integration that connects MMDetection/MMDetection3D models to Autoware/ROS 2 and couples deployment with pseudo-label active learning, demonstrated on private taxi and bus datasets.

Pith tools