AI Paper Atlas

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

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
add the weather-adaptive diffusion model to the baseline detector (ablation)MonoWAD baseline · KITTI val foggy, carAP3D Moderate: 9.61 -> 18.66Improved
add the weather codebook on top of the weather-adaptive diffusion model (ablation)MonoWAD · KITTI val foggy, carAP3D Moderate: 18.66 -> 19.57Improved
add the weather codebook on top of the weather-adaptive diffusion model (ablation)MonoWAD · KITTI val clear, carAP3D Moderate: 19.17 -> 21.08Improved
set diffusion timestep T to 15 instead of 20 (ablation)MonoWAD · KITTI val clear, carAP3D Moderate: 18.54 -> 21.08Improved
apply feature-level dehazing (DENet) to MonoDTRMonoDTR · KITTI val clear and foggy, carAP3D Moderate: foggy 11.86 -> 17.44; clear 18.57 -> 5.70Mixed
apply image-level dehazing (RIDCP) to MonoDTRMonoDTR · KITTI val clear, carAP3D Moderate: 18.57 -> 17.89Hurt
replace generic Gaussian-noise diffusion (DDPM or CDM) with weather-adaptive diffusion (ablation)MonoWAD · KITTI val foggy, carAP3D Moderate: 3.84 (DDPM) / 2.10 (CDM) -> 18.66Improved
use MonoWAD instead of MonoDTR under foggy weather on the KITTI test setmonocular 3D detection · KITTI test foggy, carAP3D Moderate: 7.41 -> 13.32Improved
use diffusion with T=15 stepsMonoWAD · inference latencyms/image: 38 (MonoDETR) -> 144Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy