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

• URL: http://arxiv.org/abs/2607.01983v1
• Date: Thu, 02 Jul 2026 10:13:41 GMT
• Title: Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment
• Abstract summary: We present Dual-Critic Guided Diffusion Alignment, a framework that learns to recover degraded LiDAR features toward a clean manifold.<n>Rather than modeling specific weather types, DCDA employs a 4D radar-conditioned diffusion process to progressively refine features.<n>A weather adversarial critic enforces holistic distributional consistency with clean-weather representations.
• Score: 20.338529072840455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection [43.35380334829282]
  We reformulate multi-modal perception as a weather-conditioned branch routing problem.<n>Our framework explicitly maintains three parallel 3D feature streams: a pure LiDAR branch, a pure 4D radar branch, and a condition-gated fusion branch.<n>Experiments on the K-Radar benchmark demonstrate that our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-07T03:56:27Z)
• LRC-WeatherNet: LiDAR, RADAR, and Camera Fusion Network for Real-time Weather-type Classification in Autonomous Driving [0.055923945039144884]
  LRC-WeatherNet is a novel multi-sensor fusion framework that integrates LiDAR, RADAR, and camera data for real-time classification of weather conditions.<n>Our approach adapts to the varying reliability of each sensor under changing weather.<n>This work is the first to combine all three modalities for robust, real-time weather classification in autonomous driving.
  arXiv  Detail & Related papers  (2026-03-23T13:49:33Z)
• Target Concept Tuning Improves Extreme Weather Forecasting [51.43578341469291]
  Deep learning models for meteorological forecasting often fail in rare but high-impact events such as typhoons.<n>Existing fine-tuning methods face a trade-off between overlooking these extreme events and overfitting them at the expense of overall performance.<n>We propose TaCT, an interpretable concept-gated fine-tuning framework that solves the aforementioned issue by selective model improvement.
  arXiv  Detail & Related papers  (2026-03-17T15:34:05Z)
• ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Data [16.145130650604344]
  We present a semantics-guided image-to-image framework for synthesizing semantically coherent, weather-diverse, and physically plausible OoD driving data.<n>Based on this framework, we construct ClimaOoD, a large-scale benchmark spanning six representative driving scenarios under both clear and adverse weather conditions.
  arXiv  Detail & Related papers  (2025-12-02T12:14:19Z)
• Nowcast3D: Reliable precipitation nowcasting via gray-box learning [43.74533335638689]
  Extreme precipitation nowcasting demands high-dimensional fidelity and extended lead times, yet existing approaches remain limited.<n>We introduce a gray-box, fully three-temporal nowcasting framework that directly processes radar motions and couples physically constrained neural operators with datadriven learning.<n>The framework achieves more accurate forecasts up to three-hour lead time in a blind evaluation by 160 meteorologists.
  arXiv  Detail & Related papers  (2025-11-06T18:44:35Z)
• RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions [58.37558408672509]
  We propose a robust self-supervised training paradigm, consisting of two key steps: robust self-supervised scene correspondence learning and adverse weather distillation.<n>Experiments demonstrate the effectiveness and versatility of our proposed solution, which outperforms existing state-of-the-art self-supervised methods.
  arXiv  Detail & Related papers  (2025-09-23T15:41:40Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Robust Single Object Tracking in LiDAR Point Clouds under Adverse Weather Conditions [4.133835011820212]
  3D single object tracking in LiDAR point clouds is a critical task for outdoor perception.<n>Despite the impressive performance of current 3DSOT methods, evaluating them on clean datasets inadequately reflects their comprehensive performance.<n>One of the main obstacles is the lack of adverse weather benchmarks for the evaluation of 3DSOT.
  arXiv  Detail & Related papers  (2025-01-13T08:44:35Z)
• Learning Real-World Image De-Weathering with Imperfect Supervision [57.748585821252824]
  Existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images. We develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image. We combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy.
  arXiv  Detail & Related papers  (2023-10-23T14:02:57Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Unpaired Adversarial Learning for Single Image Deraining with Rain-Space Contrastive Constraints [61.40893559933964]
  We develop an effective unpaired SID method which explores mutual properties of the unpaired exemplars by a contrastive learning manner in a GAN framework, named as CDR-GAN. Our method performs favorably against existing unpaired deraining approaches on both synthetic and real-world datasets, even outperforms several fully-supervised or semi-supervised models.
  arXiv  Detail & Related papers  (2021-09-07T10:00:45Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.