Pith. sign in

REVIEW 9 cited by

HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes

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 2409.19833 v2 pith:SP2AYZR7 submitted 2024-09-30 cs.CV

HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes

Changfeng Feng , Zhenyuan Chen , Xiang Li , Chunping Wang , Jian Yang , Ming-Ming Cheng , Yimian Dai , Qiang Fu This is my paper
classification cs.CV
keywords hazydetdetectionhazydecodetdomainobjectbenchmarkchallenging
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Object detection from aerial platforms under adverse atmospheric conditions, particularly haze, is paramount for robust drone autonomy. Yet, this domain remains largely underexplored, primarily hindered by the absence of specialized benchmarks. To bridge this gap, we present \textit{HazyDet}, the first, large-scale benchmark specifically designed for drone-view object detection in hazy conditions. Comprising 383,000 real-world instances derived from both naturally hazy captures and synthetically hazed scenes augmented from clear images, HazyDet provides a challenging and realistic testbed for advancing detection algorithms. To address the severe visual degradation induced by haze, we propose the Depth-Conditioned Detector (DeCoDet), a novel architecture that integrates a Depth-Conditioned Kernel to dynamically modulate feature representations based on depth cues. The practical efficacy and robustness of DeCoDet are further enhanced by its training with a Progressive Domain Fine-Tuning (PDFT) strategy to navigate synthetic-to-real domain shifts, and a Scale-Invariant Refurbishment Loss (SIRLoss) to ensure resilient learning from potentially noisy depth annotations. Comprehensive empirical validation on HazyDet substantiates the superiority of our unified DeCoDet framework, which achieves state-of-the-art performance, surpassing the closest competitor by a notable +1.5\% mAP on challenging real-world hazy test scenarios. Our dataset and toolkit are available at https://github.com/GrokCV/HazyDet.

discussion (0)

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

Forward citations

Cited by 9 Pith papers

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

  1. FRFDet: Efficient UAV Small Object Detection with Symmetric Sampling and Scalable Fusion

    cs.CV 2026-07 accept novelty 6.0

    FRFDet improves UAV small-object detection with learnable symmetric Inverse Bidirectional Sampling and capacity-dependent Scale-Feature Relationship Cross-Fusion, reaching SOTA among lightweight models.

  2. Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0

    DetAS-X uses an MLLM agent to adaptively compose detection workflows from restoration modules and expert detectors, enhanced by self-evolving experience harvesting, achieving substantial F1 score gains on challenging ...

  3. A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation

    cs.CV 2026-05 unverdicted novelty 6.0

    A dual-axis taxonomy classifies image degradations by causal source and perceptual effect, with a severity quantification layer using standard quality metrics, demonstrated via a COCO-based object detector robustness ...

  4. Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues

    cs.CV 2026-04 unverdicted novelty 6.0

    Language-guided semantic cues from MLLM visual pipelines, steered by text embeddings, refine object semantics and boost grounding accuracy against occlusion and small objects.

  5. Predictive Modeling for High Impact Active Learning Classrooms

    physics.ed-ph 2026-03 unverdicted novelty 6.0

    A model from 69 classes finds that 10-20% group worksheets, 20-40% group clicker questions, and at least two student questions per hour produce effect sizes over 2 in learning gains, while classes without group worksh...

  6. A Task-Driven Evaluation of UAV Detection and Tracking under Synthetic Fog

    cs.CV 2026-07 conditional novelty 5.0

    Fog degrades UAV detection and tracking mainly via missed detections; fog-inclusive training is more robust than test-time dehazing, and restoration quality does not proportionally improve downstream perception.

  7. Predictive Modeling for High Impact Active Learning Classrooms

    physics.ed-ph 2026-03 unverdicted novelty 5.0

    Four classroom-time variables predict physics concept learning, and classes with 10–20% group worksheets, 20–40% group clickers, and ≥2 student questions per hour show effect sizes above 2.

  8. FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection

    cs.CV 2025-09 unverdicted novelty 5.0

    FMC-DETR proposes a frequency-decoupled fusion framework with WeKat backbone, MDFC coordination, and CPF fusion modules that claims state-of-the-art results on remote sensing object detection benchmarks.

  9. UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning

    cs.CV 2025-08 unverdicted novelty 5.0

    UAV-VL-R1 combines SFT and multi-stage GRPO reinforcement learning on a new 50,019-sample HRVQA-VL dataset to deliver substantially higher zero-shot accuracy on UAV visual reasoning tasks than both its 2B baseline and...