The reviewed record of science sign in
Pith

arxiv: 2606.31096 · v1 · pith:MV5U4Y2N · submitted 2026-06-30 · cs.CV

Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving

Geonho Bang , Geunju Baek , Dongyoung Lee , Wonjun Jeong , Jun Won Choi This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-07-01 06:14 UTCgrok-4.3pith:MV5U4Y2Nrecord.jsonopen to challenge →

classification cs.CV
keywords radar-camera fusion3D object detectionautonomous drivinglong-range perceptionGaussian primitivesBEV featurestemporal fusionTruckScenes
0
0 comments X

The pith

Horizon3D fuses radar and camera keypoints into Gaussian primitives that are refined and splatted onto sparse BEV features to lift long-range 3D detection.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that a sparse radar-camera fusion method can overcome the trade-off between scene-level context and fine object detail in long-range 3D object detection. It does so by initializing Gaussian primitives at estimated keypoints from both sensors, refining them with object-centric sparse fusion, splatting the results onto a BEV plane, and handling time through separate BEV and Gaussian paths. A sympathetic reader would care because highway-speed autonomous driving requires reliable detection hundreds of meters ahead, where current BEV methods grow too expensive and query methods lose context. Experiments on TruckScenes report concrete gains of 3.0 NDS and 1.6 mAP over the prior best method at competitive speed.

Core claim

Horizon3D initializes Gaussian primitives at radar- and camera-estimated object keypoints using Keypoint-Guided Gaussian Initialization, refines them through Object-Centric Sparse Fusion, and splats them onto the BEV plane to fuse object-level detail with sparse radar BEV context; it further aggregates temporal cues via Dual-Path Temporal Fusion along a BEV path for scene accumulation and a Gaussian path for object motion propagation.

What carries the argument

Keypoint-Guided Gaussian Initialization combined with Object-Centric Sparse Fusion and Dual-Path Temporal Fusion

Load-bearing premise

Radar and camera keypoint estimates are accurate enough and complementary on the TruckScenes validation set to preserve fine object detail while adding scene context.

What would settle it

A direct measurement on TruckScenes showing that the radar and camera keypoint estimates have high error or low complementarity, such that removing or degrading them eliminates the reported NDS and mAP gains.

Figures

Figures reproduced from arXiv: 2606.31096 by Dongyoung Lee, Geonho Bang, Geunju Baek, Jun Won Choi, Wonjun Jeong.

Figure 1
Figure 1. Figure 1: Comparison of radar-camera fusion paradigms. [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overall architecture of Horizon3D. Multi-view camera images and 4D radar points are encoded by their respective backbones. The KGGI module estimates object keypoints from both modalities and initializes sparse Gaussian primitives at these locations. The OCSF module aggregates cross-modal features around the Gaussians and produces a sparse BEV representation that captures both object-level detail and scene-… view at source ↗
Figure 3
Figure 3. Figure 3: Details of Object-Centric Splatting and Velocity-Guided Temporal [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparison of temporally aggregated BEV feature maps [PITH_FULL_IMAGE:figures/full_fig_p014_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Detailed architecture of the BEV-path temporal aggregation module. This section describes the BEV-path temporal aggregation module introduced in Section 3.3 of the main paper. As illustrated in [PITH_FULL_IMAGE:figures/full_fig_p020_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative comparison on TruckScenes validation set. [PITH_FULL_IMAGE:figures/full_fig_p024_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Failure cases on TruckScenes validation set. [PITH_FULL_IMAGE:figures/full_fig_p025_7.png] view at source ↗
read the original abstract

Long-range 3D object detection is critical for safe autonomous driving at highway speeds, yet existing radar-camera fusion methods remain limited at extended ranges. BEV-based methods capture scene-level context but incur rapidly growing computation and often lose fine-grained object detail, while query-based methods are efficient but provide limited scene-level context. Temporal fusion further requires both multi-frame accumulation for sparse distant observations and object-level motion modeling for fast-moving objects. We propose Horizon3D, a sparse radar-camera fusion framework for long-range 3D object detection that combines Gaussian primitives with sparse BEV features. Horizon3D initializes Gaussian primitives at radar- and camera-estimated object keypoints using Keypoint-Guided Gaussian Initialization, refines them through Object-Centric Sparse Fusion, and splats them onto the BEV plane to fuse object-level detail with sparse radar BEV context. It further introduces Dual-Path Temporal Fusion, which aggregates temporal cues through a BEV path for scene-level accumulation and a Gaussian path for object-level motion propagation. Experiments on TruckScenes show that Horizon3D achieves state-of-the-art radar-camera 3D detection performance. On the validation set, it outperforms the previous best method by +3.0 NDS and +1.6 mAP while maintaining competitive inference speed.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 0 minor

Summary. Horizon3D proposes a sparse radar-camera fusion framework for long-range 3D object detection. It initializes Gaussian primitives at radar- and camera-estimated object keypoints via Keypoint-Guided Gaussian Initialization, refines them through Object-Centric Sparse Fusion, splats them onto the BEV plane to combine object detail with sparse radar context, and employs Dual-Path Temporal Fusion (BEV path for scene accumulation and Gaussian path for object motion). Experiments on TruckScenes claim state-of-the-art radar-camera 3D detection, outperforming the prior best by +3.0 NDS and +1.6 mAP on the validation set at competitive speed.

Significance. If substantiated, the approach could meaningfully advance long-range perception by addressing the trade-off between fine object detail and scene-level context in radar-camera fusion while handling temporal sparsity for distant objects.

major comments (2)
  1. Abstract: The central performance claim (+3.0 NDS and +1.6 mAP gains) is stated without any reference to experimental protocol, validation split details, baseline re-implementations, error bars, or statistical significance, making the SOTA assertion unverifiable from the manuscript text.
  2. Method section (Keypoint-Guided Gaussian Initialization and Object-Centric Sparse Fusion): The premise that these components successfully preserve object detail while incorporating long-range context rests on the untested assumption that radar- and camera-derived keypoints are sufficiently accurate (low localization error relative to object scale) and complementary on TruckScenes. No quantitative keypoint error metrics (e.g., mean distance to GT centers) or ablations isolating their contribution are supplied.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their detailed and constructive feedback. We address each major comment point-by-point below, indicating where revisions will be made to strengthen the manuscript.

read point-by-point responses

  1. Referee: Abstract: The central performance claim (+3.0 NDS and +1.6 mAP gains) is stated without any reference to experimental protocol, validation split details, baseline re-implementations, error bars, or statistical significance, making the SOTA assertion unverifiable from the manuscript text.

    Authors: We agree that the abstract would benefit from greater specificity to allow readers to assess the claims directly. In the revised manuscript we will expand the abstract to explicitly state that results are reported on the TruckScenes validation set, that all baselines were re-implemented using their official code and recommended protocols, and that the reported gains are measured under the standard evaluation protocol described in Section 4. We will also note that error bars are omitted following common practice in the field when single-run results are presented, while directing readers to the full experimental details. revision: yes

  2. Referee: Method section (Keypoint-Guided Gaussian Initialization and Object-Centric Sparse Fusion): The premise that these components successfully preserve object detail while incorporating long-range context rests on the untested assumption that radar- and camera-derived keypoints are sufficiently accurate (low localization error relative to object scale) and complementary on TruckScenes. No quantitative keypoint error metrics (e.g., mean distance to GT centers) or ablations isolating their contribution are supplied.

    Authors: The referee is correct that the current manuscript does not supply direct quantitative keypoint localization errors or an ablation that isolates the Keypoint-Guided Gaussian Initialization step. While the overall performance improvements and the existing fusion ablations provide supporting evidence, we will add both a quantitative keypoint accuracy analysis (reporting mean distance to ground-truth centers for radar- and camera-derived keypoints) and a dedicated ablation isolating the initialization component in the revised version. revision: yes

Circularity Check

0 steps flagged

No circularity detected; derivation is self-contained

full rationale

The manuscript presents Horizon3D as a proposed architecture (Keypoint-Guided Gaussian Initialization, Object-Centric Sparse Fusion, Dual-Path Temporal Fusion) whose performance is asserted via empirical results on the TruckScenes validation set. No equations, fitted parameters renamed as predictions, self-citations used as load-bearing uniqueness theorems, or ansatzes smuggled via prior work appear in the provided text. The central claims therefore do not reduce to their own inputs by construction and remain externally falsifiable.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

Abstract-only review prevents identification of concrete free parameters, axioms, or invented entities beyond the high-level components named; no numerical fits or background lemmas are stated.

invented entities (1)
  • Gaussian primitives no independent evidence
    purpose: Represent object keypoints for fusion and splatting
    Named in the method description as the core representation

pith-pipeline@v0.9.1-grok · 5775 in / 1199 out tokens · 26434 ms · 2026-07-01T06:14:51.842118+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

45 extracted references · 45 canonical work pages

  1. [1]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Alibeigi, M., Ljungbergh, W., Tonderski, A., Hess, G., Lilja, A., Lindström, C., Motorniuk, D., Fu, J., Widahl, J., Petersson, C.: Zenseact Open Dataset: A large- scale and diverse multimodal dataset for autonomous driving. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 20178–20188 (2023)

    work page 2023

  2. [2]

    IEEE Robotics and Automation Letters10(1), 828–835 (2025)

    Bai, X., Yu, Z., Zheng, L., Zhang, X., Zhou, Z., Zhang, X., Wang, F., Bai, J., Shen, H.L.: SGDet3D: Semantics and geometry fusion for 3d object detection using 4d radar and camera. IEEE Robotics and Automation Letters10(1), 828–835 (2025)

    work page 2025

  3. [3]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2026) 16 G

    Bai, X., Zhou, C., Zheng, L., Liu, J., Cao, S.Y., Zhang, X., Li, Y., Zhang, Z., Shen, H.L.: RaGS: Unleashing 3D gaussian splatting from 4D radar and monocular cue for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2026) 16 G. Bang et al

    work page 2026

  4. [4]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Bang, G., Seong, M., Kim, J., Baek, G., Oh, D., Kim, J., Koh, J., Choi, J.W.: RCT- Distill: Cross-modal knowledge distillation framework for radar-camera 3D object detection with temporal fusion. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 25315–25324 (2025)

    work page 2025

  5. [5]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., Beijbom, O.: nuScenes: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 11621–11631 (2020)

    work page 2020

  6. [6]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Chen, Y., Liu, J., Zhang, X., Qi, X., Jia, J.: VoxelNeXt: Fully sparse voxelnet for 3d object detection and tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 21674–21683 (2023)

    work page 2023

  7. [7]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Chu, X., Deng, J., You, G., Duan, Y., Li, H., Zhang, Y.: RaCFormer: Towards high- quality 3d object detection via query-based radar-camera fusion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 17081–17091 (2025)

    work page 2025

  8. [8]

    Advances in Neural Information Processing Systems35, 351–363 (2022)

    Fan, L., Wang, F., Wang, N., Zhang, Z.X.: Fully sparse 3d object detection. Advances in Neural Information Processing Systems35, 351–363 (2022)

    work page 2022

  9. [9]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops

    Fent, F., Bauerschmidt, P., Lienkamp, M.: RadarGNN: Transformation invariant graph neural network for radar-based perception. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 182–191 (2023)

    work page 2023

  10. [10]

    Advances in Neural Information Processing Systems37, 62062–62082 (2024)

    Fent, F., Kuttenreich, F., Ruch, F., Rizwin, F., Juergens, S., Lechermann, L., Nissler, C., Perl, A., Voll, U., Yan, M., Lienkamp, M.: MAN TruckScenes: a multimodal dataset for autonomous trucking in diverse conditions. Advances in Neural Information Processing Systems37, 62062–62082 (2024)

    work page 2024

  11. [11]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770–778 (2016)

    work page 2016

  12. [12]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Huang, Y., Thammatadatrakoon, A., Zheng, W., Zhang, Y., Du, D., Lu, J.: GaussianFormer-2: Probabilistic gaussian superposition for efficient 3d occupancy prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 27477–27486 (2025)

    work page 2025

  13. [13]

    In: European Conference on Computer Vision

    Huang, Y., Zheng, W., Zhang, Y., Zhou, J., Lu, J.: GaussianFormer: Scene as gaus- sians for vision-based 3D semantic occupancy prediction. In: European Conference on Computer Vision. pp. 376–393 (2024)

    work page 2024

  14. [14]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Jiang, X., Li, S., Liu, Y., Wang, S., Jia, F., Wang, T., Han, L., Zhang, X.: Far3D: Expanding the horizon for surround-view 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 38, pp. 2561–2569 (2024)

    work page 2024

  15. [15]

    In: Proceedings of the IEEE International Conference on Robotics and Automation

    Kim, J., Seong, M., Bang, G., Kum, D., Choi, J.W.: RCM-Fusion: Radar-camera multi-level fusion for 3d object detection. In: Proceedings of the IEEE International Conference on Robotics and Automation. pp. 18236–18242 (2024)

    work page 2024

  16. [16]

    Advances in Neural Information Processing Systems37, 108625–108648 (2024)

    Kim, J., Seong, M., Choi, J.W.: CRT-Fusion: Camera, radar, temporal fusion using motion information for 3d object detection. Advances in Neural Information Processing Systems37, 108625–108648 (2024)

    work page 2024

  17. [17]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Kim, Y., Shin, J., Kim, S., Lee, I.J., Choi, J.W., Kum, D.: CRN: Camera radar net for accurate, robust, efficient 3d perception. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 17615–17626 (2023)

    work page 2023

  18. [18]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops

    Lee, Y., Hwang, J.w., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 752–760 (2019) Horizon3D 17

    work page 2019

  19. [19]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Li, Y., Yang, Y., Lei, Z.: RCTrans: Radar-camera transformer via radar densifier and sequential decoder for 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 5048–5056 (2025)

    work page 2025

  20. [20]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Li, Z., Lan, S., Alvarez, J.M., Wu, Z.: BEVNeXt: Reviving dense BEV frameworks for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 20113–20123 (2024)

    work page 2024

  21. [21]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Lin, Z., Liu, Z., Xia, Z., Wang, X., Wang, Y., Qi, S., Dong, Y., Dong, N., Zhang, L., Zhu, C.: RCBEVDet: Radar-camera fusion in bird’s eye view for 3d object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14928–14937 (2024)

    work page 2024

  22. [22]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Liu, S., Cui, M., Li, B., Liang, Q., Hong, T., Huang, K., Shan, Y., Huang, K.: FSHNet: Fully sparse hybrid network for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8900–8909 (2025)

    work page 2025

  23. [23]

    In: European Conference on Computer Vision

    Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: Position embedding transformation for multi-view 3d object detection. In: European Conference on Computer Vision. pp. 531–548 (2022)

    work page 2022

  24. [24]

    Advances in Neural Information Processing Systems37, 13601–13626 (2024)

    Liu, Z., Hou, J., Wang, X., Ye, X., Wang, J., Zhao, H., Bai, X.: LION: Linear group RNN for 3D object detection in point clouds. Advances in Neural Information Processing Systems37, 13601–13626 (2024)

    work page 2024

  25. [25]

    In: Pro- ceedings of the IEEE International Conference on Robotics and Automation

    Liu, Z., Tang, H., Amini, A., Yang, X., Mao, H., Rus, D.L., Han, S.: BEVFusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation. In: Pro- ceedings of the IEEE International Conference on Robotics and Automation. pp. 2774–2781 (2023)

    work page 2023

  26. [26]

    IEEE Robotics and Automation Letters7(2), 4961–4968 (2022)

    Palffy, A., Pool, E., Baratam, S., Kooij, J.F., Gavrila, D.M.: Multi-class road user detection with 3+1D radar in the View-of-Delft dataset. IEEE Robotics and Automation Letters7(2), 4961–4968 (2022)

    work page 2022

  27. [27]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Palladin, E., Brucker, S., Ghilotti, F., Narayanan, P., Bijelic, M., Heide, F.: Self- supervised sparse sensor fusion for long range perception. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 27498–27509 (2025)

    work page 2025

  28. [28]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Wang, H., Shi, C., Shi, S., Lei, M., Wang, S., He, D., Schiele, B., Wang, L.: DSVT: Dynamic sparse voxel transformer with rotated sets. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13520–13529 (2023)

    work page 2023

  29. [29]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Wang, H., Gao, J., Hu, W., Zhang, Z.: Height-fidelity dense global fusion for multi-modal 3d object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 26664–26674 (2025)

    work page 2025

  30. [30]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops

    Wang, T., Zhu, X., Pang, J., Lin, D.: FCOS3D: Fully convolutional one-stage monocular 3D object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. pp. 913–922 (2021)

    work page 2021

  31. [31]

    In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021) (2021)

    Wilson, B., Qi, W., Agarwal, T., Lambert, J., Singh, J., Khandelwal, S., Pan, B., Kumar, R., Hartnett, A., Pontes, J.K., Ramanan, D., Carr, P., Hays, J.: Argoverse 2: Next generation datasets for self-driving perception and forecasting. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benc...

    work page 2021

  32. [32]

    In: Proceedings of the IEEE International Conference on Robotics and Automation

    Wolters, P., Gilg, J., Teepe, T., Herzog, F., Fent, F., Rigoll, G.: SpaRC: Sparse radar- camera fusion for 3D object detection. In: Proceedings of the IEEE International Conference on Robotics and Automation. pp. 6589–6596 (2026)

    work page 2026

  33. [33]

    Bang et al

    Wolters, P., Gilg, J., Teepe, T., Herzog, F., Laouichi, A., Hofmann, M., Rigoll, G.: Unleashing HyDRa: Hybrid fusion, depth consistency and radar for unified 3d 18 G. Bang et al. perception. In: Proceedings of the IEEE International Conference on Robotics and Automation. pp. 7467–7474 (2025)

    work page 2025

  34. [34]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Xie, Y., Xu, C., Rakotosaona, M.J., Rim, P., Tombari, F., Keutzer, K., Tomizuka, M., Zhan, W.: SparseFusion: Fusing multi-modal sparse representations for multi-sensor 3d object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 17591–17602 (2023)

    work page 2023

  35. [35]

    IEEE Transactions on Intelligent Vehicles9(1), 79–92 (2024)

    Xiong, W., Liu, J., Huang, T., Han, Q.L., Xia, Y., Zhu, B.: LXL: Lidar excluded lean 3d object detection with 4d imaging radar and camera fusion. IEEE Transactions on Intelligent Vehicles9(1), 79–92 (2024)

    work page 2024

  36. [36]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Yang, Z., Yu, Z., Choy, C., Wang, R., Anandkumar, A., Alvarez, J.M.: Improving distant 3D object detection using 2D box supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14853– 14863 (2024)

    work page 2024

  37. [37]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3d object detection and tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 11784–11793 (2021)

    work page 2021

  38. [38]

    Advances in Neural Information Processing Systems36, 53076–53089 (2023)

    Zhang,G.,Chen,J.,Gao,G.,Li,J.,Hu,X.:HEDNet:Ahierarchicalencoder-decoder network for 3d object detection in point clouds. Advances in Neural Information Processing Systems36, 53076–53089 (2023)

    work page 2023

  39. [39]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zhang, G., Chen, J., Gao, G., Li, J., Liu, S., Hu, X.: SAFDNet: A simple and effective network for fully sparse 3d object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14477–14486 (2024)

    work page 2024

  40. [40]

    Advances in Neural Information Processing Systems37, 81489–81509 (2024)

    Zhang, G., Fan, L., He, C., Lei, Z., Zhang, Z., Zhang, L.: Voxel Mamba: Group-free state space models for point cloud based 3d object detection. Advances in Neural Information Processing Systems37, 81489–81509 (2024)

    work page 2024

  41. [41]

    In: European Conference on Computer Vision

    Zhang, H., Liang, L., Zeng, P., Song, X., Wang, Z.: SparseLIF: High-performance sparse lidar-camera fusion for 3d object detection. In: European Conference on Computer Vision. pp. 109–128 (2024)

    work page 2024

  42. [42]

    In: International Conference on Learning Representations (2026)

    Zhao, X., Liu, C., Zhu, M., Zhang, Z., Song, L., Luo, Q., Guo, C., Su, K.: Gaus- sianFusion: Unified 3D gaussian representation for multi-modal fusion perception. In: International Conference on Learning Representations (2026)

    work page 2026

  43. [43]

    In: IEEE International Conference on Intelligent Transportation Systems

    Zheng, L., Ma, Z., Zhu, X., Tan, B., Li, S., Long, K., Sun, W., Chen, S., Zhang, L., Wan, M., et al.: TJ4DRadSet: A 4d radar dataset for autonomous driving. In: IEEE International Conference on Intelligent Transportation Systems. pp. 493–498 (2022)

    work page 2022

  44. [44]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Zhong, H., Xiang, Z., Xu, R., Fu, J., Xu, P., Wang, S., Yang, Z., Pu, T., Liu, E.: CVFusion: Cross-view fusion of 4D radar and camera for 3D object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 28188–28197 (2025)

    work page 2025

  45. [45]

    Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: Deformable transformers for end-to-end object detection. In: International Conference on Learn- ing Representations (2021) Horizon3D 19 Supplementary Material for Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving This supplementary material provides...

    work page 2021