Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View

TL;DR

Top2Pano is an end-to-end model that synthesizes realistic indoor 360-degree panoramas from top-down views by estimating 3D structure and refining with diffusion models, outperforming baselines.

Contribution

The paper introduces Top2Pano, a novel approach combining volumetric occupancy estimation and diffusion-based refinement for indoor panorama generation from top-down views.

Findings

Outperforms baseline methods in geometry and realism

Generalizes well to schematic floorplans

Produces high-quality immersive panoramas

Abstract

Generating immersive 360{\deg} indoor panoramas from 2D top-down views has applications in virtual reality, interior design, real estate, and robotics. This task is challenging due to the lack of explicit 3D structure and the need for geometric consistency and photorealism. We propose Top2Pano, an end-to-end model for synthesizing realistic indoor panoramas from top-down views. Our method estimates volumetric occupancy to infer 3D structures, then uses volumetric rendering to generate coarse color and depth panoramas. These guide a diffusion-based refinement stage using ControlNet, enhancing realism and structural fidelity. Evaluations on two datasets show Top2Pano outperforms baselines, effectively reconstructing geometry, occlusions, and spatial arrangements. It also generalizes well, producing high-quality panoramas from schematic floorplans. Our results highlight Top2Pano's potential in bridging top-down views with immersive indoor synthesis.