Research map / Detection and segmentation / 3D detection and driving
MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection
Youngmin Oh, Hyung-Il Kim, Seong Tae Kim, Jung Uk Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the weather-adaptive diffusion model to the baseline detector (ablation) | MonoWAD baseline · KITTI val foggy, car | AP3D Moderate: 9.61 -> 18.66 | Improved |
| add the weather codebook on top of the weather-adaptive diffusion model (ablation) | MonoWAD · KITTI val foggy, car | AP3D Moderate: 18.66 -> 19.57 | Improved |
| add the weather codebook on top of the weather-adaptive diffusion model (ablation) | MonoWAD · KITTI val clear, car | AP3D Moderate: 19.17 -> 21.08 | Improved |
| set diffusion timestep T to 15 instead of 20 (ablation) | MonoWAD · KITTI val clear, car | AP3D Moderate: 18.54 -> 21.08 | Improved |
| apply feature-level dehazing (DENet) to MonoDTR | MonoDTR · KITTI val clear and foggy, car | AP3D Moderate: foggy 11.86 -> 17.44; clear 18.57 -> 5.70 | Mixed |
| apply image-level dehazing (RIDCP) to MonoDTR | MonoDTR · KITTI val clear, car | AP3D Moderate: 18.57 -> 17.89 | Hurt |
| replace generic Gaussian-noise diffusion (DDPM or CDM) with weather-adaptive diffusion (ablation) | MonoWAD · KITTI val foggy, car | AP3D Moderate: 3.84 (DDPM) / 2.10 (CDM) -> 18.66 | Improved |
| use MonoWAD instead of MonoDTR under foggy weather on the KITTI test set | monocular 3D detection · KITTI test foggy, car | AP3D Moderate: 7.41 -> 13.32 | Improved |
| use diffusion with T=15 steps | MonoWAD · inference latency | ms/image: 38 (MonoDETR) -> 144 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- MonoDTR — MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer (CVPR 2022) · better on 8 of 8 shared results
- MonoDETR — MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (ICCV 2023) · better on 4 of 4 shared results
- GUPNet — GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection (TPAMI 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.86)
- Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection (AAAI 2024 · similarity 0.86)
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · similarity 0.85)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · similarity 0.85)
- UAWTrack: Universal 3D Single Object Tracking in Adverse Weather (AAAI 2025 · similarity 0.85)
- Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
