• Home
  • Search
  • Pano3R: Training Free Panoramic 3D Reconstruction
  • Cite Icon1
  • https://doi.org/10.3233/faia250852Copy DOI Icon

Pano3R: Training Free Panoramic 3D Reconstruction

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Panoramic 3D reconstruction is essential for immersive scene understanding in robotics, AR, and autonomous driving. However, most existing methods are designed for pinhole images and generalize poorly to 360° inputs due to the scarcity of panoramic training data and the high cost of retraining. We present Pano3R, the first training-free framework for panoramic 3D reconstruction that adapts existing pinhole-based models without any retraining. Pano3R consists of two stages. Specifically, the pre-processing stage applies a position-aware pairing strategy to decompose each panorama into a minimal set of perspective views. These views are selected to ensure sufficient co-visible regions while minimizing the number of projections. The test-time optimization stage incorporates a pose-prior-guided global alignment strategy to improve global consistency and mitigate accumulated errors. Our method enables accurate 360° reconstruction under both single- and multi-view input conditions. Extensive experiments demonstrate that Pano3R consistently improves reconstruction accuracy and pose estimation quality, establishing a strong and practical benchmark for training-free panoramic 3D reconstruction.

Similar Papers
  • Conference Article

DepthVision3D: a versatile deep learning dataset for 3D imaging

  • Jan 01, 2025
  • Shaun Wang +3
  • Conference Article
  • Citations41

Fine tuning CNNS with scarce training data — Adapting imagenet to art epoch classification

  • Sep 01, 2016
  • Christian Hentschel +2
  • Research Article

Scale-consistent 3D reconstruction in monocular colonoscopy via camera-intrinsics-guided learning.

  • Mar 01, 2026
  • Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
  • Yeqi Liu +4
  • Research Article

Tools and Methods for Achieving Wi-Fi Sensing in Embedded Devices.

  • Oct 08, 2025
  • Sensors (Basel, Switzerland)
  • Jesus A Armenta-Garcia +3
  • Conference Article
  • Citations2

Reconstructing Graph Diffusion History from a Single Snapshot

  • Aug 04, 2023
  • Ruizhong Qiu +5
  • Research Article
  • Citations1

Threat intelligence named entity recognition techniques based on few-shot learning

  • Sep 01, 2024
  • Array
  • Haiyan Wang +4
  • Research Article

Computational Visual Ceramicology: Matching Image Outlines to Catalog Sketches

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Barak Itkin +2
  • Research Article
  • Citations6

Machine Translation Performance for Low-Resource Languages: A Systematic Literature Review

  • Jan 01, 2025
  • IEEE Access
  • Taofik O Tafa +8
  • Video Transcripts

AraBench: Benchmarking Dialectal Arabic-English Machine Translation

  • Nov 25, 2020
  • Underline Science Inc.
  • Fahim Dalvi +3
  • Research Article

RealUHR: Harnessing Patch-Cascade Flows for Photorealistic Ultra-High-Resolution Synthesis

  • Mar 14, 2026
  • Yongsheng Yu +6
  • Conference Article
  • Citations20

Adaptive Online Runtime Prediction to Improve HPC Applications Latency in Cloud

  • Jul 01, 2018
  • Mina Naghshnejad +1
  • Research Article
  • Citations8

The role of machine learning in automated code checking – a systematic literature review

  • Jan 08, 2025
  • Journal of Information Technology in Construction
  • Maen Alnuzha +1
  • Research Article
  • Citations21

ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection.

  • Jan 01, 2024
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Zhimeng Xin +5
  • PDF
  • Research Article
  • Citations3

Coping with AI errors with provable guarantees

  • Jun 03, 2024
  • Information Sciences
  • Ivan Y Tyukin +8
  • Conference Article

Limited-view Cone Beam CT reconstruction using 3D Patch-based Supervised and Adversarial Learning

  • Jan 01, 2021
  • Anish Lahiri +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.