arXiv AI

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

The paper introduces PaGeR, a framework that adapts pre‑trained 3D reconstruction transformers to handle both perspective and panoramic images. PaGeR predicts scale‑invariant depth, metric depth, surface normals, and sky masks in a single forward pass, using minimal architectural changes and mixed‑domain training. Extensive indoor and outdoor tests show state‑of‑the‑art and strong zero‑shot performance across diverse scenes.

Hugging Face Trending Papers
Jul 9

Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction

Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisition and computation. Adopting panoramic images with equirectangular projection (ERP) can reduce capture effort via their full $360^{\circ}$ field of view, yet the resulting omnipresent visibility invalidates existing partitioning strategies that rely on local camera frustums, causing block-wise optimization to degenerate into global training.

arXiv Computer Vision
Oct 16

GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single Panorama

GeoPano is a feed‑forward framework that reconstructs geometrically accurate 3D point clouds from a single panoramic image. It introduces a panoramic‑aware attention aggregator with a novel Pano‑Attention mechanism to exploit spherical geometry and reduce cross‑view inconsistencies. A hybrid supervision strategy enforces both fine‑grained local detail in perspective views and global structural coherence in spherical space, leading to superior reconstruction accuracy, consistency, and visual fidelity compared to prior state‑of‑the‑art methods.

By Jing OU, Zidong Cao, Liaoyuan Fan, Zhuoxiao Li, Shuai Zhang, Yinrui Ren, Dongli Wu, Haoang Li, Hui Xiong, Wufan Zhao
arXiv Computer Vision
Oct 28

HoloRecon: Incremental Reconstruction of Long-Range Panoramas with Global Consistency

HoloRecon proposes a panoramic reconstruction framework that merges ORB-based sparse mapping with a fine-tuned feed-forward model to achieve accurate localization and globally consistent dense mapping over long sequences. By using predicted local geometry for 3D verification of feature matches, the method establishes long-range camera constraints even between distant revisits, calibrates depths with sparse landmarks, and optimizes a global pose graph. The authors also introduce PanoRecon, a seven-scene benchmark for evaluating global consistency, and report that HoloRecon achieves the lowest mean absolute trajectory error and high F‑1 Score among evaluated methods.

By Zhuoxiao Li, Xinyi Liu, Hongye Hou, Jing OU, Kang Du, Shuai Zhang, Dongli Wu, Taoyu Wu, Siyuan Feng, Xiaohui Zhu, Wufan Zhao
arXiv Computer Vision
Nov 6

A 3D-Driven Framework for Moving-Camera Perspective-to-360{\deg} Video Generation

The paper introduces a modular, 3D-driven framework for converting moving-camera perspective videos into 360° videos. It separates the tasks of preserving observed content, plausibly completing unseen regions, and maintaining consistency across viewpoints into specialized components linked by a shared 3D scene representation. The approach reconstructs input observations in 3D, uses a pretrained panoramic image model to fill missing areas, and lifts the completed content into the shared scene, achieving state‑of‑the‑art fidelity and consistency without extra panoramic‑video training.

By Michael Wakeham, Mrinmoy Kumar Das, Wenqi Wang, Ayush Tewari, Boqing Gong, Deepti Ghadiyaram
arXiv Computer Vision
Oct 28

Any3R: Feedforward 3D Reconstruction from Any Camera Type

Any3R is a feed‑forward 3D reconstruction model that works with any central camera type, regardless of lens distortion or field‑of‑view limits. It conditions on a dense ray field—unit direction vectors through every pixel—so its positional encoding and loss function are lens‑agnostic. Evaluated on thirteen camera types across three datasets, Any3R consistently outperforms other methods, enabling scalable reconstruction from heterogeneous, crowdsourced imagery.

By Jingong Chen, Qingwen Zhang, Youming Deng, Chulwoo Pack, Olaf Wysocki, Boris Jutzi, Kwanghee Won, Kyle Gao
arXiv AI
Oct 15

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

arXiv:2604.14025v2 Announce Type: replace-cross Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understa...

By Weijie Wang, Qihang Cao, Sensen Gao, Donny Y. Chen, Haofei Xu, Wenjing Bian, Songyou Peng, Tat-Jen Cham, Chuanxia Zheng, Andreas Geiger, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang
arXiv Computer Vision
Oct 15

Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence

arXiv:2610.19502v1 Announce Type: new Abstract: Spatial intelligence requires scalable 3D environments that are both photorealistic and semantically grounded, yet existing indoor datasets are dominat...

By Yuanyuan Gao, Zhirui Liu, Yuning Gong, Yifei Liu, Yifan Zhan, Kuixuan Jiao, Xiaolong Zhou, Yifan Yang, Hongjie Zhang, Xue Yang, Dan Xu, Zhihang Zhong
arXiv Computer Vision
Aug 31

GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping

GeoFF3D is a new feed‑forward 3D reconstruction method designed for large‑scale UAV mapping. It uses a coordinate‑anchored model that predicts camera poses and dense point maps directly in a gravity‑aligned Z‑up metric frame, while a spatial large‑scale reconstruction framework (SLRF) partitions images into overlapping chunks, propagates shared‑view priors, and aggregates local reconstructions hierarchically. Across nine aerial mapping blocks, GeoFF3D achieves the best average reconstruction quality, improving F@5 from 0.829 to 0.877, and can reconstruct 2,000 images in about five minutes.

By Xiang Yang, Yongli Wang, Yunsheng Zhang