AI/ 3d generation · computer vision · diffusion models · spatial ai

One Panorama, Full 3D Scene - Pano2World Skips the Iterative Steps

A new research method turns a single indoor panorama into a navigable 3D scene in one pass, sidestepping the error buildup that plagues existing pipelines.

A new paper from arXiv proposes turning a single 360-degree photo into a fully explorable 3D environment without the multi-step hand-holding most current methods require.

The system, called Pano2World, takes one indoor panoramic image and outputs what researchers call a "3D Gaussian scene" - a compact geometric representation that supports free-viewpoint navigation. It first builds a rough 3D proxy from the source image, renders that proxy from nearby angles to generate guidance frames, then runs a diffusion model that denoises all target views at once rather than one at a time. A module called Latent Feature Adapter pulls geometric information directly from the model's internal hidden states, skipping a lossy decoding step that comparable approaches rely on. On a standard benchmark for panoramic novel-view synthesis, the method outperforms existing alternatives.

The practical gap being closed here is meaningful: current approaches either chain inpainting steps together - letting errors compound with each iteration - or borrow from video generation models, which are optimized for smooth forward trajectories and struggle to cover a scene from multiple directions at once. Pano2World's joint denoising step addresses both problems in a single forward pass. That matters for anyone building virtual tours, real-estate previews, or spatial AI training data who currently has to babysit a brittle pipeline.

This is academic research, so production readiness is a separate question - but the architecture borrows heavily from diffusion and Gaussian splatting work that has moved from paper to product faster than most expected.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →