AI Paper Atlas

Research map / 3D vision / Depth and stereo

ULTRA-360: Unconstrained Dataset for Large-scale Temporal 3D Reconstruction across Altitudes and Omnidirectional Views

Xijun Liu, Zhaoliang Zhang, Yuxiang Guo, Yifan Zhou, Rama Chellappa, Cheng Peng

ICLR 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction

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 SuperPoint or DaD keypoint filtering to RoMa matches (ablation)RoMa · ULTRA-360 cross-elevation matchingAUC@10: 0.0854 -> 0.6941 (Building #10)Improved
use classic or other matchers (SIFT, SP+SG, LoFTR) instead of RoMa-based ones (ablation)cross-elevation calibration · ULTRA-360 cross-elevation matchingAUC@10: 0 AUC@10 on all seven buildingsHurt
train on ground+aerial images instead of single elevation (ablation)Octree-GS, Scaffold-GS, Block-MERF · ULTRA-360 aerial testPSNR: Block-MERF 27.451 -> 13.453; Octree-GS 29.950 -> 26.488Hurt
train on ground+aerial instead of ground only (ablation)Octree-GS · ULTRA-360 ground testPSNR: 21.360 -> 21.184No clear effect
combine ground and aerial training data (ablation)Gaussian splatting methods · ULTRA-360number of Gaussians: EVER 535701 (G) -> 262366 (GA)Hurt
add implicit neural sky model (ablation)Octree-GS · ULTRA-360 aerial renderings from ground-only reconstructionfloaters (qualitative)Improved
use farthest training image embedding instead of test image embedding (ablation)Wild-GS · ULTRA-360 multi-appearancePSNR: 28.133 -> 22.506Hurt
use farthest training image embedding instead of test image embedding (ablation)Gaussian-Wild · ULTRA-360 multi-appearancePSNR: 26.528 -> 25.621Hurt
replace per-image embedding with time-based embedding (ablation)Wild-GS · ULTRA-360 multi-appearancePSNR: 28.133 -> 27.973No clear effect
add rotation points to Procrustes alignment (ablation)Procrustes Alignment · Mip-NeRF 360 sparse alignmentrotation error ER: 0.196 -> 0.156Improved
add RANSAC to Procrustes alignment (ablation)Procrustes Alignment · Mip-NeRF 360 sparse alignmentrotation error ER: 0.196 -> 0.179Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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