AI Paper Atlas

Research map / 3D vision / Depth and stereo

Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning

Dongki Jung, Jaehoon Choi, Adil Qureshi, Somi Jeong, Dinesh Manocha, Suyong Yeon

ECCV 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 6 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 camera model tokens (ablation)Wid3R · Stanford2D3D ablation (360)Acc. mean: 0.284 -> 0.248Improved
add camera model tokens (ablation)Wid3R · Stanford2D3D ablation (360)N.C. mean: 0.680 -> 0.706Improved
add pinhole data to 360-only training (ablation)Wid3R · Stanford2D3D ablation (360)Comp. mean: 0.355 -> 0.166Improved
add pinhole data to 360-only training (ablation)Wid3R · Stanford2D3D ablation (360)Acc. mean: 0.220 -> 0.254Hurt
add fisheye data to 360-only training (ablation)Wid3R · Stanford2D3D ablation (360)Comp. mean: 0.355 -> 0.120Improved
add fisheye data to 360-only training (ablation)Wid3R · Stanford2D3D ablation (360)Acc. mean: 0.220 -> 0.593Hurt
add pinhole and fisheye data to 360-only training (ablation)Wid3R · Stanford2D3D ablation (360)Comp. mean: 0.355 -> 0.146Improved
add pinhole and fisheye data to 360-only training (ablation)Wid3R · Stanford2D3D ablation (360)Acc. std. mean: 0.187 -> 0.089Improved
increase frames per batch from 12 to 24 (ablation)Wid3R · Stanford2D3D ablation (360)Acc. mean: 0.248 -> 0.197Improved
increase frames per batch from 12 to 24 (ablation)Wid3R · Stanford2D3D ablation (360)Comp. mean: 0.146 -> 0.172Hurt
replace point map head with ray-based angular/radial modules and camera tokens (ablation)pi3 trained on wide-FoV data · Stanford2D3D zero-shot poseAUC@30: 62.14 -> 79.93Improved
replace point map head with ray-based angular/radial modules and camera tokens (ablation)pi3 trained on wide-FoV data · FIORD zero-shot poseAUC@30: 72.56 -> 68.20Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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