pith. sign in

arxiv: 2607.01983 · v1 · pith:4B7LNROVnew · submitted 2026-07-02 · 💻 cs.CV

Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment

Shuyao Li , Chuanxing Geng , Heyang Sun , Qiang Zhou , Jingjing Gu This is my paper

Pith reviewed 2026-07-03 15:35 UTC · model grok-4.3

classification 💻 cs.CV
keywords 3D object detectionadverse weatherdiffusion modelsLiDAR feature alignmentradar fusionrobust perceptionopen-world generalizationadversarial critic
0
0 comments X

The pith

A diffusion process guided by detection and adversarial critics aligns degraded LiDAR features to clean distributions for robust 3D detection in unseen weather.

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

Autonomous driving needs 3D detection that holds up when test weather differs from training data, since rain, fog, or snow create unpredictable LiDAR degradation patterns. The paper presents Dual-Critic Guided Diffusion Alignment to progressively refine those degraded features back toward a clean manifold through a radar-conditioned diffusion model. One critic keeps the refined features accurate for object detection by referencing a pre-trained clean model, while the second critic pushes the overall feature distribution to match clean weather statistics. The approach requires neither paired clean-degraded scans nor any weather labels or type-specific modeling. If successful, detectors could maintain performance across arbitrary weather combinations without retraining for each new condition.

Core claim

DCDA recovers degraded LiDAR features toward a clean manifold via a 4D radar-conditioned diffusion process guided by a detection critic anchored in a pre-trained clean-weather model and a weather adversarial critic that enforces distributional consistency, allowing generalization to unseen weather types and severities without paired data or weather labels.

What carries the argument

Dual-Critic Guided Diffusion Alignment (DCDA), a diffusion refinement process steered by semantic discriminability from object detection and distributional consistency from adversarial learning.

If this is right

  • The method generalizes to arbitrary weather without explicit modeling of degradation patterns or weather categories.
  • Training requires no paired clean-adverse examples or weather labels, only access to a clean pre-trained detector.
  • Refined features preserve both object localization accuracy and class discriminability through the dual constraints.
  • A structured benchmark with held-out type-severity combinations can be used to measure open-weather robustness.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The critic-guided diffusion idea could extend to recovering features degraded by other factors such as sensor aging or calibration drift.
  • Similar alignment without paired data might reduce the cost of collecting diverse training sets for perception in new geographic regions.
  • The framework suggests testing whether the same critics can stabilize multi-modal fusion when one sensor degrades more than others.
  • It points toward perception modules that adapt online by continuously referencing a fixed clean manifold rather than retraining.

Load-bearing premise

The pre-trained clean-weather detection model and the weather adversarial critic can reliably steer the diffusion process to produce features that remain both discriminative for detection tasks and statistically consistent with clean data for any unseen weather.

What would settle it

Detection performance on a held-out weather type-severity pair shows no meaningful gain over the non-aligned baseline or the original degraded features, indicating the critics did not produce usable alignment.

Figures

Figures reproduced from arXiv: 2607.01983 by Chuanxing Geng, Heyang Sun, Jingjing Gu, Qiang Zhou, Shuyao Li.

Figure 1
Figure 1. Figure 1: Open-weather generalization gap on K-Radar. The top and bottom rows show BEV AP for L4DR and V2X-R, respectively, under the three protocols shown from left to right: type-open, severity-open, and type+severity-open. Closed-set denotes each detector’s conventional closed-set baseline, where the test weather conditions are seen during training. Ours denotes the proposed DCDA model under the corresponding ope… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of DCDA. The radar-conditioned diffusion alignment refines LiDAR BEV features, guided by a frozen detection critic and a frozen normal-weather discrim￾inator. a comparatively stable signal. DCDA consists of (i) a radar-conditioned dif￾fusion alignment Aθ for iterative refinement, and (ii) a dual-critic guidance toward the clean manifold during training: a detection-guided critic H that en￾forces s… view at source ↗
Figure 3
Figure 3. Figure 3: Inference of DCDA with optional routing. When the input is confidently Nor￾mal, DCDA can be bypassed to reduce unnecessary refinement [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Parameter sensitivity analysis on K-Radar type-open: mean BEV/3D AP (%) on seen and unseen weather types. 4.3 Ablation Study We perform ablation studies to analyze the contribution of each component in DCDA [PITH_FULL_IMAGE:figures/full_fig_p013_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative BEV detections on a real K-Radar Rain scene (type-open). Columns: ground truth (dashed gray), w/o DCDA, and DCDA (Ours). Green: matched predictions; red: false positives. Numbers: matched-GT out of total GT objects. 10 0 10 Before DCDA 0 20 40 60 (a) Normal 10 0 10 After DCDA 0 20 40 60 (b) Sleet 0 20 40 60 (c) HeavySnow 0.0 0.2 0.4 0.6 0.8 1.0 [PITH_FULL_IMAGE:figures/full_fig_p014_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Visualization on K-Radar type-open: intermediate BEV feature maps before (top) and after (bottom) applying DCDA under (a) Normal, (b) Sleet, (c) HeavySnow weather conditions [PITH_FULL_IMAGE:figures/full_fig_p014_6.png] view at source ↗
read the original abstract

Robust 3D object detection under adverse weather remains a critical hurdle for autonomous driving. Despite progress with LiDAR-4D radar fusion, most methods are constrained by a closed-world assumption, implicitly requiring training and test weather to align in both type and severity. This premise fails in practice: the open-ended nature of weather, and even variations within a single type like rain, cause dramatically different LiDAR degradation patterns, leading to significant performance drops in unseen conditions. To address this, we present Dual-Critic Guided Diffusion Alignment (DCDA), a weather-agnostic framework that learns to recover degraded LiDAR features toward a clean manifold. Rather than modeling specific weather types, DCDA employs a 4D radar-conditioned diffusion process to progressively refine features, guided by two complementary critics. (i) A detection-guided critic, anchored by a pre-trained clean-weather model, ensures that the refined features retain object-level discriminability and localization accuracy. (ii) A weather adversarial critic enforces holistic distributional consistency with clean-weather representations. By aligning features through semantic and distributional constraints rather than explicit weather modeling, DCDA generalizes effectively to unseen weather types and severities without requiring paired data or weather labels. We further introduce a structured open-weather benchmark with held-out type-severity combinations and extensive experiments verify DCDA's advantages.

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 / 2 minor

Summary. The paper proposes Dual-Critic Guided Diffusion Alignment (DCDA), a weather-agnostic framework for robust 3D object detection from LiDAR under open-ended adverse weather. It employs a 4D radar-conditioned diffusion process to refine degraded features toward a clean manifold, guided by (i) a fixed pre-trained clean-weather detection critic that preserves object discriminability and (ii) an adversarial distributional critic that enforces consistency with clean representations. The method is trained without paired weather data or labels and is evaluated on a new structured open-weather benchmark that holds out type-severity combinations.

Significance. If the empirical claims hold, the work would be significant for autonomous-driving perception: it replaces explicit weather modeling and paired-data requirements with semantic-plus-distributional alignment inside a diffusion process, offering a falsifiable route to generalization across unseen weather variations.

major comments (2)
  1. [Abstract and §4] Abstract and §4 (Experiments): the central performance claim that DCDA 'generalizes effectively to unseen weather types and severities' is load-bearing, yet the visible text supplies no quantitative results, error bars, baseline comparisons, or ablation numbers on the held-out splits; without these the generalization argument cannot be assessed.
  2. [Methods] Methods (diffusion guidance): the claim that the two critics together produce features that remain discriminative for unseen weather rests on the unexamined assumption that a fixed clean-weather detector plus an adversarial critic suffice; the paper must show, via controlled ablations, that removing either critic measurably degrades held-out performance.
minor comments (2)
  1. [Abstract] Abstract: the phrase 'extensive experiments verify DCDA's advantages' is vague; replace with one or two concrete metrics (e.g., mAP on held-out rain-severity-3) to give readers an immediate sense of the result.
  2. [Methods] Notation: the description of the 'weather adversarial critic' does not specify whether it operates on feature statistics, latent codes, or reconstructed point clouds; a short equation or diagram would clarify the distributional loss.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address the two major comments below by clarifying the experimental evidence and committing to targeted revisions that strengthen the presentation of results and ablations.

read point-by-point responses

  1. Referee: [Abstract and §4] Abstract and §4 (Experiments): the central performance claim that DCDA 'generalizes effectively to unseen weather types and severities' is load-bearing, yet the visible text supplies no quantitative results, error bars, baseline comparisons, or ablation numbers on the held-out splits; without these the generalization argument cannot be assessed.

    Authors: We acknowledge that the abstract, per standard practice, contains no numerical results. However, §4 of the full manuscript reports quantitative evaluations on the held-out type-severity splits, including comparisons against baselines. To address the concern directly, we will revise §4 to include a consolidated table of held-out performance metrics with standard error bars computed over multiple random seeds, plus explicit baseline numbers. This addition will make the generalization evidence immediately verifiable without altering the underlying experiments. revision: yes

  2. Referee: [Methods] Methods (diffusion guidance): the claim that the two critics together produce features that remain discriminative for unseen weather rests on the unexamined assumption that a fixed clean-weather detector plus an adversarial critic suffice; the paper must show, via controlled ablations, that removing either critic measurably degrades held-out performance.

    Authors: We agree that explicit ablations are required to substantiate the necessity of both critics. The current manuscript contains an ablation study, but it does not isolate the effect of each critic on the held-out splits. In the revision we will add controlled experiments that remove the detection-guided critic and the adversarial critic individually, reporting the resulting drops in mAP and other metrics on the unseen weather combinations. These new results will be presented in §4 alongside the main tables. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The abstract and description present a high-level framework using a pre-trained clean-weather detector as one critic and a weather adversarial critic for a radar-conditioned diffusion process. No equations, derivations, fitted parameters renamed as predictions, or load-bearing self-citations appear in the text. The generalization to unseen weather is scoped to a held-out benchmark split, which is an external falsifiable setup rather than a reduction to the method's own inputs by construction. The central claim remains independent of any self-referential loop.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no specific free parameters, axioms, or invented entities can be identified or audited from the provided text.

pith-pipeline@v0.9.1-grok · 5774 in / 1162 out tokens · 27155 ms · 2026-07-03T15:35:35.763334+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

44 extracted references · 44 canonical work pages

  1. [1]

    In: Proceedings of the Com- puter Vision and Pattern Recognition Conference

    Batten, B., Lomuscio, A.: Improving weather-based ood generalisation in lidar- based object detection models via adversarial training. In: Proceedings of the Com- puter Vision and Pattern Recognition Conference. pp. 4321–4329 (2025)

    work page 2025

  2. [2]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Bijelic, M., Gruber, T., Mannan, F., Kraus, F., Ritter, W., Dietmayer, K., Heide, F.: Seeing through fog without seeing fog: Deep multimodal sensor fusion in unseen adverse weather. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 11682–11692 (2020)

    work page 2020

  3. [3]

    In: European Conference on Computer Vision

    Chae, Y., Kim, H., Oh, C., Kim, M., Yoon, K.J.: Lidar-based all-weather 3d ob- ject detection via prompting and distilling 4d radar. In: European Conference on Computer Vision. pp. 368–385. Springer (2024)

    work page 2024

  4. [4]

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

    Chae, Y., Kim, H., Yoon, K.J.: Towards robust 3d object detection with lidar and 4d radar fusion in various weather conditions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 15162–15172 (2024)

    work page 2024

  5. [5]

    In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision

    Chae, Y., Park, H., Kim, H., Yoon, K.J.: Doppler-aware lidar-radar fusion for weather-robust 3d detection. In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision. pp. 27197–27208 (2025)

    work page 2025

  6. [6]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Chang, G., Roh, W., Jang, S., Lee, D., Ji, D., Oh, G., Park, J., Kim, J., Kim, S.: Cmda: Cross-modal and domain adversarial adaptation for lidar-based 3d ob- ject detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 38, pp. 972–980 (2024)

    work page 2024

  7. [7]

    Advances in Neural Information Processing Systems37, 103681–103705 (2024)

    Chen, X., Liu, Z., Luo, K., Datta, S., Polavaram, A., Wang, Y., You, Y., Li, B., Pavone, M., Chao, W.L.H., et al.: Diffubox: Refining 3d object detection with point diffusion. Advances in Neural Information Processing Systems37, 103681–103705 (2024)

    work page 2024

  8. [8]

    arXiv preprint arXiv:2406.14878 (2024)

    Chen, Z., Meng, J., Baktashmotlagh, M., Zhang, Y., Huang, Z., Luo, Y.: Mos: Model synergy for test-time adaptation on lidar-based 3d object detection. arXiv preprint arXiv:2406.14878 (2024)

    work page arXiv 2024

  9. [9]

    In: Proceedings of the 32nd ACM International Conference on Multimedia

    Chen, Z., Wang, Z., Luo, Y., Wang, S., Huang, Z.: Dpo: dual-perturbation opti- mization for test-time adaptation in 3d object detection. In: Proceedings of the 32nd ACM International Conference on Multimedia. pp. 4138–4147 (2024)

    work page 2024

  10. [10]

    Advances in Neural Information Processing Systems 37, 101589–101617 (2024)

    Ding, F., Wen, X., Zhu, Y., Li, Y., Lu, C.X.: Radarocc: Robust 3d occupancy pre- diction with 4d imaging radar. Advances in Neural Information Processing Systems 37, 101589–101617 (2024)

    work page 2024

  11. [11]

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

    Dong, Y., Kang, C., Zhang, J., Zhu, Z., Wang, Y., Yang, X., Su, H., Wei, X., Zhu, J.: Benchmarking robustness of 3d object detection to common corruptions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 1022–1032 (2023)

    work page 2023

  12. [12]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Hahner, M., Sakaridis, C., Bijelic, M., Heide, F., Yu, F., Dai, D., Van Gool, L.: Lidar snowfall simulation for robust 3d object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 16364– 16374 (2022)

    work page 2022

  13. [13]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Hahner, M., Sakaridis, C., Dai, D., Van Gool, L.: Fog simulation on real lidar point clouds for 3d object detection in adverse weather. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 15283–15292 (2021)

    work page 2021

  14. [14]

    arXiv preprint arXiv:2306.04242 , year=

    Han, Z., Wang, J., Xu, Z., Yang, S., He, L., Xu, S., Wang, J., Li, K.: 4d millimeter- wave radar in autonomous driving: A survey. arXiv preprint arXiv:2306.04242 (2023) Open-Weather Robust 3D Detection 17

    work page arXiv 2023

  15. [15]

    arXiv preprint arXiv:2512.13107 (2025)

    He, Z., Liu, F., Li, Y., Luo, Z., Cheng, J., Chen, X., Tang, X.: Diffusion-based restoration for multi-modal 3d object detection in adverse weather. arXiv preprint arXiv:2512.13107 (2025)

    work page arXiv 2025

  16. [16]

    The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences48, 733–740 (2023)

    Huang, H., Yan, X., Yang, J., Cao, Y., Zhang, X.: Lidsor: A filter for removing rain and snow noise points from lidar point clouds in rainy and snowy weather. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences48, 733–740 (2023)

    work page 2023

  17. [17]

    arXiv preprint arXiv:2202.02703 (2022)

    Huang, K., Shi, B., Li, X., Li, X., Huang, S., Li, Y.: Multi-modal sensor fusion for auto driving perception: A survey. arXiv preprint arXiv:2202.02703 (2022)

    work page arXiv 2022

  18. [18]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Huang, X., Wang, J., Xia, Q., Chen, S., Yang, B., Li, X., Wang, C., Wen, C.: V2x-r: Cooperative lidar-4d radar fusion with denoising diffusion for 3d object detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 27390–27400 (2025)

    work page 2025

  19. [19]

    In: Proceedings of the AAAI conference on artificial intelligence

    Huang, X., Xu, Z., Wu, H., Wang, J., Xia, Q., Xia, Y., Li, J., Gao, K., Wen, C., Wang, C.: L4dr: Lidar-4dradar fusion for weather-robust 3d object detection. In: Proceedings of the AAAI conference on artificial intelligence. vol. 39, pp. 3806–3814 (2025)

    work page 2025

  20. [20]

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

    Kong, L., Liu, Y., Li, X., Chen, R., Zhang, W., Ren, J., Pan, L., Chen, K., Liu, Z.: Robo3d: Towards robust and reliable 3d perception against corruptions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 19994–20006 (2023)

    work page 2023

  21. [21]

    arXiv preprint arXiv:2404.13852 (2024)

    Lee, E., Jung, M., Kim, A.: Toward robust lidar based 3d object detection via density-aware adaptive thresholding. arXiv preprint arXiv:2404.13852 (2024)

    work page arXiv 2024

  22. [22]

    In: International Conference on Neural Information Processing

    Matteazzi, A., Arnold, M., Tutsch, D.: Augmentation of lidar scenes with adverse weather conditions using latent diffusion models. In: International Conference on Neural Information Processing. pp. 198–212. Springer (2025)

    work page 2025

  23. [23]

    In: European Conference on Com- puter Vision

    Oh, Y., Kim, H.I., Kim, S.T., Kim, J.U.: Monowad: Weather-adaptive diffusion model for robust monocular 3d object detection. In: European Conference on Com- puter Vision. pp. 326–345. Springer (2024)

    work page 2024

  24. [24]

    arXiv preprint arXiv:2502.00074 (2025)

    Paek, D.H., Kong, S.H.: Spikingrtnh: Spiking neural network for 4d radar object detection. arXiv preprint arXiv:2502.00074 (2025)

    work page arXiv 2025

  25. [25]

    Advances in Neural Information Processing Systems35, 3819–3829 (2022)

    Paek, D.H., Kong, S.H., Wijaya, K.T.: K-radar: 4d radar object detection for au- tonomous driving in various weather conditions. Advances in Neural Information Processing Systems35, 3819–3829 (2022)

    work page 2022

  26. [26]

    In: Euro- pean Conference on Computer Vision

    Palladin, E., Dietze, R., Narayanan, P., Bijelic, M., Heide, F.: Samfusion: Sensor- adaptive multimodal fusion for 3d object detection in adverse weather. In: Euro- pean Conference on Computer Vision. pp. 484–503. Springer (2024)

    work page 2024

  27. [27]

    In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Sig- nal Processing (ICASSP)

    Peng, X., Sun, H., Bierzynski, K., Fischbacher, A., Servadei, L., Wille, R.: Mu- tualforce: Mutual-aware enhancement for 4d radar-lidar 3d object detection. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Sig- nal Processing (ICASSP). pp. 1–5. IEEE (2025)

    work page 2025

  28. [28]

    arXiv e-prints pp

    Peng, X., Tang, M., Sun, H., Servadei, L., Wille, R.: 4d mmwave radar in adverse environments for autonomous driving: A survey. arXiv e-prints pp. arXiv–2503 (2025)

    work page 2025

  29. [29]

    arXiv preprint arXiv:2505.09422 (2025)

    Peng, X., Wang, Y., Tang, M., Kay, B., Servadei, L., Wille, R.: Moral: Motion- aware multi-frame 4d radar and lidar fusion for robust 3d object detection. arXiv preprint arXiv:2505.09422 (2025)

    work page arXiv 2025

  30. [30]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Peng, X., Zhu, X., Ma, Y.: Cl3d: Unsupervised domain adaptation for cross-lidar 3d detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 37, pp. 2047–2055 (2023) 18 S. Li et al

    work page 2047

  31. [31]

    IEEE Robotics and Automation Letters8(7), 4322–4329 (2023)

    Piroli, A., Dallabetta, V., Kopp, J., Walessa, M., Meissner, D., Dietmayer, K.: Energy-based detection of adverse weather effects in lidar data. IEEE Robotics and Automation Letters8(7), 4322–4329 (2023)

    work page 2023

  32. [32]

    Transportation research part C: emerging technologies161, 104555 (2024)

    Qi, Y., Liu, C., Scaioni, M., Li, Y., Qiao, Y., Ma, X., Wu, H., Zhang, K., Wang, D.: Geometric information constraint 3d object detection from lidar point cloud for autonomous vehicles under adverse weather. Transportation research part C: emerging technologies161, 104555 (2024)

    work page 2024

  33. [33]

    Information Fusion p

    Qi, Y., Liu, C., Wu, H., Chen, R., Wen, C., Huang, X., Jia, S., Zhang, K.: Fu- sionbev: Lidar and 4d radar fusion for 3d object detection. Information Fusion p. 104240 (2026)

    work page 2026

  34. [34]

    In: 2024 IEEE in- telligent vehicles symposium (IV)

    Sural, S., Sahu, N., Rajkumar, R.R.: Contextualfusion: Context-based multi-sensor fusion for 3d object detection in adverse operating conditions. In: 2024 IEEE in- telligent vehicles symposium (IV). pp. 1534–1541. IEEE (2024)

    work page 2024

  35. [35]

    In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

    Wang, L., Zhang, X., Xv, B., Zhang, J., Fu, R., Wang, X., Zhu, L., Ren, H., Lu, P., Li, J., et al.: Interfusion: Interaction-based 4d radar and lidar fusion for 3d object detection. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 12247–12253. IEEE (2022)

    work page 2022

  36. [36]

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

    Wang, Y., Deng, J., Li, Y., Hu, J., Liu, C., Zhang, Y., Ji, J., Ouyang, W., Zhang, Y.: Bi-lrfusion: Bi-directional lidar-radar fusion for 3d dynamic object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13394–13403 (2023)

    work page 2023

  37. [37]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Wu, Y., Zhu, Y., Zhang, K., Qian, J., Xie, J., Yang, J.: Weathergen: A unified diverse weather generator for lidar point clouds via spider mamba diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 17019–17028 (2025)

    work page 2025

  38. [38]

    IET Image Processing20(1), e70257 (2026)

    Wu, Y., Sun, W., Zhong, Z., Li, Q.: Pasenet: Snowy scene 3d object detection with pillar-wise attention and semantic enhancement. IET Image Processing20(1), e70257 (2026)

    work page 2026

  39. [39]

    In: European Conference on Computer Vision

    Xu, R., Xiang, Z.: Rlnet: Adaptive fusion of 4d radar and lidar for 3d object detection. In: European Conference on Computer Vision. pp. 181–194. Springer (2024)

    work page 2024

  40. [40]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Ye, X., Yaman, B., Cheng, S., Tao, F., Mallik, A., Ren, L.: Bevdiffuser: Plug-and- play diffusion model for bev denoising with ground-truth guidance. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 1495–1504 (2025)

    work page 2025

  41. [41]

    Yuan, J., Zhang, B., Gong, K., Yue, X., Shi, B., Qiao, Y., Chen, T.: Reg-tta3d: Betterregressionmakesbettertest-timeadaptive3dobjectdetection.In:European conference on computer vision. pp. 197–213. Springer (2024)

    work page 2024

  42. [42]

    Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering p

    Zhang, B., Wang, Y., Zhang, C., Jiang, J., Luo, X., Wang, X., Zhang, Y., Liu, Z., Shen, G., Ye, Y., et al.: Fogfusion: Robust 3d object detection based on camera- lidar fusion for autonomous driving in foggy weather conditions. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering p. 09544070251327229 (2025)

    work page 2025

  43. [43]

    In: Proceedings of the Asian Conference on Computer Vision

    Zhang, Z., Gong, H., Feng, Y., Chu, Z., Liu, H.: Enhancing object detection in adverse weather conditions through entropy and guided multimodal fusion. In: Proceedings of the Asian Conference on Computer Vision. pp. 2922–2938 (2024)

    work page 2024

  44. [44]

    In: Proceedings of the AAAI conference on artificial intelligence

    Zou, J., Tian, K., Zhu, Z., Ye, Y., Wang, X.: Diffbev: Conditional diffusion model for bird’s eye view perception. In: Proceedings of the AAAI conference on artificial intelligence. vol. 38, pp. 7846–7854 (2024)

    work page 2024