AI Paper Atlas

Research map / 3D vision / Depth and stereo

OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras

Chaesong Park, Jihyeon Hwang, Muyeol Sung, Jongwoo Lim

ECCV 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 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
use both CNN and DINO as context instead of CNN only (ablation)OmniDS · Sunny ablationMAE: 0.38 -> 0.35Improved
use both CNN and DINO context instead of CNN only (ablation)OmniDS · Sunny ablation>1 error: 5.06 -> 4.69Improved
use CNN similarity instead of DINO similarity (ablation)OmniDS · Sunny ablationMAE: 0.51 -> 0.38Improved
add multi-view consensus volume (MVC) to CNN+DINO context (ablation)OmniDS · Sunny ablation>1 error: 4.69 -> 4.60Improved
add MVC to CNN+DINO context (ablation)OmniDS · Sunny ablationRMS: 1.55 -> 1.63Hurt
add deformable cross-attention with distortion bias (ablation)OmniDS · Sunny ablation>1 error: 4.60 -> 4.49Improved
add 2D spatial aggregation to correlation profile (ablation)OmniDS · Sunny ablation (similarity volumes)>1 error: 5.00 -> 4.67Improved
add MVC to Corr + 2D Aggr. (ablation)OmniDS · Sunny ablation (similarity volumes)>1 error: 4.67 -> 4.49Improved
add MVC to Corr + 2D Aggr. (ablation)OmniDS · Sunny ablation (similarity volumes)RMS: 1.52 -> 1.59Hurt
distill dual-stream encoder into MobileNet studentOmniDS Ours-ft · OmniThings (fine-tuned)MAE: 1.70 -> 2.11Hurt
distill dual-stream encoder into MobileNet studentOmniDS Ours-ft · inference timetime (ms): 148 -> 102Improved
distill dual-stream encoder into MobileNet studentOmniDS Ours-ft · OmniHouse (fine-tuned)>1 error: 3.92 -> 3.41Improved

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