Pith. sign in

REVIEW 6 cited by

DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention

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 2212.07849 v1 pith:FLMVLKF4 submitted 2022-12-15 cs.CV

Zhipeng Luo , Changqing Zhou , Gongjie Zhang , Shijian Lu This is my paper · ORCID
classification cs.CV
keywords objectdetectiondetr4dattentiondirectfeaturesimagesinformation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in multi-view images. We design a novel projective cross-attention mechanism for query-image interaction to address the limitations of existing methods in terms of geometric cue exploitation and information loss for cross-view objects. In addition, we introduce a heatmap generation technique that bridges 3D and 2D spaces efficiently via query initialization. Furthermore, unlike the common practice of fusing intermediate spatial features for temporal aggregation, we provide a new perspective by introducing a novel hybrid approach that performs cross-frame fusion over past object queries and image features, enabling efficient and robust modeling of temporal information. Extensive experiments on the nuScenes dataset demonstrate the effectiveness and efficiency of the proposed DETR4D.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. MambaMap: Online Vectorized HD Map Construction using State Space Model

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MambaMap fuses four previous frames of BEV features and instance queries via gated state space layers, beating prior HD map construction methods on nuScenes and Argoverse2.

  2. OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception

    cs.CV 2025-07 conditional novelty 6.0 of 10

    OnlineBEV achieves state-of-the-art 3D object detection on nuScenes by recurrently fusing bird's eye view features with motion-guided deformable attention and a heatmap consistency loss.

  3. S2GO: Streaming Sparse Gaussian Occupancy Prediction

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A sparse-query, streaming Gaussian occupancy predictor achieves state-of-the-art 3D semantic occupancy on nuScenes and KITTI with real-time inference.

  4. SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset

    cs.CV 2025-02 conditional novelty 6.0 of 10

    SimBEV is a randomized synthetic data generation tool and a 320-scene, 102,400-frame dataset with eight-class BEV segmentation and 3D bounding box annotations.

  5. EVT: Efficient View Transformation for Multi-Modal 3D Object Detection

    cs.CV 2024-11 conditional novelty 6.0 of 10

    EVT achieves state-of-the-art 75.3% NDS on the nuScenes test set by using LiDAR-guided adaptive sampling and projection for image-to-BEV transformation, along with a geometry-aware transformer decoder.

  6. MambaDETR: Query-based Temporal Modeling using State Space Model for Multi-View 3D Object Detection

    cs.CV 2024-11 conditional novelty 5.0 of 10

    MambaDETR applies a Mamba/SSM sequence model to temporal fusion of 3D detection queries, achieving 50.8 mAP on nuScenes val with 8 frames and linear memory scaling.

Pith tools