PanoLoop: Yaw‐Invariant Loop Closure for Feed‐Forward Panoramic SLAM

Abstract Feed‐forward models such as VGGT recover camera poses and dense geometry in a single pass, and recent systems extend them into SLAM front‐ends for long pinhole sequences. Panoramic video is an even more natural fit—one 360 ° view captures the full surround and needs no intrinsic calibration—yet no feed‐forward SLAM system exists for it. We show that the crux is loop closure: well handled by pinhole pipelines, but uniquely hard on panoramas. Revisits are seen from arbitrary headings, where standard place descriptors, tied to viewing direction, fail; we therefore propose YIP, whose Fourier magnitude is exactly invariant to integer token‐grid shifts and, up to discretization, approximately invariant to physical yaw. But this invariance cuts both ways: blind to heading, it also matches look‐alike yet distant places, which an anchor‐free backbone, with no sense of absolute position, aligns into false loops. The obvious defense is to verify each candidate's geometry—our multi‐signal verifier (MSV) does, rejecting many—but no per‐candidate test is perfect, and across a flood of candidates these residual errors still admit enough false loops to corrupt the trajectory. Our key finding is that the cure is not a stronger verifier but an earlier one: candidate‐stage suppression first collapses the flood, so that MSV—now judging only a handful—becomes decisive. This sparsify‐then‐verify order beats both verifying the full flood and gating loops after pose‐graph optimization, when the trajectory is already corrupted. We call the resulting method PanoLoop. On 360Loc, it turns near‐non‐functional panoramic loop closure into an effective one, improving camera tracking over a strong panoramic visual‐odometry baseline and producing globally consistent panoramic reconstructions.

Authors

Institutions

Publication Details

Journal
Computer Graphics Forum
Published
2026-11-13
DOI
https://doi.org/10.1111/cgf.70607
Primary Topic
Robotics and Sensor-Based Localization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

PanoLoop: Yaw‐Invariant Loop Closure for Feed‐Forward Panoramic SLAM

Dianxi Shi, Mengzhu Wang, Yuetian Wang, Yuanze Wang et al.
4 links
Computer Graphics Forum
Robotics and Sensor-Based Localization
article

PanoLoop: Yaw‐Invariant Loop Closure for Feed‐Forward Panoramic SLAM

Dianxi Shi, Mengzhu Wang, Yuetian Wang, Yuanze Wang, Chunping Qiu, Shiming Song, Yongjun Zhang, Haikuo Peng
article en

Abstract

Abstract Feed‐forward models such as VGGT recover camera poses and dense geometry in a single pass, and recent systems extend them into SLAM front‐ends for long pinhole sequences. Panoramic video is an even more natural fit—one 360 ° view captures the full surround and needs no intrinsic calibration—yet no feed‐forward SLAM system exists for it. We show that the crux is loop closure: well handled by pinhole pipelines, but uniquely hard on panoramas. Revisits are seen from arbitrary headings, where standard place descriptors, tied to viewing direction, fail; we therefore propose YIP, whose Fourier magnitude is exactly invariant to integer token‐grid shifts and, up to discretization, approximately invariant to physical yaw. But this invariance cuts both ways: blind to heading, it also matches look‐alike yet distant places, which an anchor‐free backbone, with no sense of absolute position, aligns into false loops. The obvious defense is to verify each candidate's geometry—our multi‐signal verifier (MSV) does, rejecting many—but no per‐candidate test is perfect, and across a flood of candidates these residual errors still admit enough false loops to corrupt the trajectory. Our key finding is that the cure is not a stronger verifier but an earlier one: candidate‐stage suppression first collapses the flood, so that MSV—now judging only a handful—becomes decisive. This sparsify‐then‐verify order beats both verifying the full flood and gating loops after pose‐graph optimization, when the trajectory is already corrupted. We call the resulting method PanoLoop. On 360Loc, it turns near‐non‐functional panoramic loop closure into an effective one, improving camera tracking over a strong panoramic visual‐odometry baseline and producing globally consistent panoramic reconstructions.

Computer Graphics Forum
National University of Defense Technology (CN), Shanghai Jiao Tong University (CN), Hebei University of Technology (CN)
Robotics and Sensor-Based Localization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon