AI Paper Atlas

Research map / 3D vision / Depth and stereo

SEDiff: Structure Extraction for Domain Adaptive Depth Estimation via Denoising Diffusion Models

Dongseok Shim, Hyoun Jin Kim

ECCV 2024 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 0 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
feed extracted structural content instead of raw RGB to the depth network (ablation)SEDiff · KITTI Eigen test (80m)Abs Rel: 0.268 -> 0.165Improved
convert input to grayscale before the geometric feature extractor (ablation)SEDiff · KITTI Eigen test (80m)Abs Rel: 0.268 -> 0.231Improved
train G with diffusion instead of using the LDM autoencoder encoder E (ablation)SEDiff · KITTI Eigen test (80m)Abs Rel: 0.183 -> 0.165Improved
latent-level instead of pixel-level diffusion (ablation)SEDiff · KITTI Eigen test (80m)Abs Rel: 0.166 -> 0.165No clear effect
estimate attention map from style-transferred image rather than raw synthetic image (ablation)SEDiff · KITTI Eigen test (80m)Abs Rel: 0.173 -> 0.168Improved
ensemble depth from both synthetic and style-transferred inputs (ablation)SEDiff · KITTI Eigen test (80m)Abs Rel: 0.168 -> 0.165Improved
SEDiff vs 3D-PL on KITTI with monocular real imagesSEDiff · KITTI Eigen test (80m)Abs Rel / Sq Rel: Abs Rel 0.169 -> 0.165; Sq Rel 1.262 -> 1.301Mixed
add real stereo pairs to trainingSEDiff · KITTI Eigen test (80m)Abs Rel: 0.165 -> 0.110Improved
SEDiff vs 3D-PL on unseen DrivingStereoSEDiff · DrivingStereo (unseen)Abs Rel: 0.243 -> 0.193Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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