AI Paper Atlas

Research map / 3D vision / Depth and stereo

PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery

Yijing Guo, Mengjun Chao, Luo Wang, Tianyang Zhao, Haizhao Dai, Yingliang Zhang, Jingyi Yu, Yujiao Shi

CVPR 2026 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 10 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 PanoCity training data to panoramic pi3 (ablation)pi3* · Matterport3D (3 views)Abs Rel: 0.194 -> 0.105Improved
add tri-axis SO(3) rotation augmentation (ablation)pi3* + PanoCity · Matterport3D (3 views)AUC@30: 0.256 -> 0.285Improved
add tri-axis SO(3) rotation augmentation (ablation)pi3* + PanoCity · Matterport3D (3 views)mean translation error (deg): 31.52 -> 35.04Hurt
add global point fusion head (ablation)PanoVGGT ablation chain · Matterport3D (3 views)AUC@30: 0.285 -> 0.380Improved
add spherical sin-cos positional embedding (ablation)PanoVGGT ablation chain · Matterport3D (3 views)AUC@30: 0.380 -> 0.427Improved
retrain pi3 on panoramic data (pi3*) vs original pi3pi3 · Matterport3D poseAUC@30: 0.047 -> 0.305Improved
use native panoramic PanoVGGT instead of pinhole pi3 via dodecahedral projectionpi3 · PanoCity point cloudOverall mean: 8.222 -> 0.737Improved
use multi-view instead of monocular inputPanoVGGT · Stanford2D3D depthAbs Rel: 0.0711 -> 0.0778Mixed
unified PanoVGGT vs per-dataset depth-only modelsPanoVGGT · Structured3D depthAbs Rel: 0.0273 (EGFormer) vs 0.0438Hurt

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