PanoLess: Environment Reconstruction from Partial Reflective Views

2026-07-28

AI Summary

This work addresses the challenge of reconstructing full environmental illumination from a single partial reflection image, which suffers from limited viewpoints and geometric inconsistencies. The authors propose PanoLess, a novel framework that, for the first time, enables recovery of physically consistent far-field environment lighting using only partial reflective views. PanoLess models scene geometry via surface-aligned 2D Gaussian splats, leverages deferred shading to extract per-pixel normals and reflection cues, and fuses these into a neural cubemap representation while simultaneously generating an explicit visibility map to identify valid observation regions. Experiments on both a newly constructed synthetic dataset and public benchmarks demonstrate that PanoLess outperforms existing reflection-aware methods and generalizes effectively to real-world images, achieving high-fidelity and geometrically consistent environment lighting reconstruction.

Abstract

Reflections from shiny objects and glass facades naturally extend the field of view of a camera, capturing the surrounding environment without the need to pan the camera or acquire a full panorama. We propose PanoLess, a Gaussian-splat-based framework that reconstructs the surrounding environment as a distant illumination map from images captured on only one side of a reflective surface. PanoLess leverages surface-aligned 2D Gaussian splats with deferred shading to recover accurate per-pixel normals and reflection cues, which are fused into a neural cubemap representation of the environment. In addition, PanoLess produces a visibility map that explicitly denotes which regions of the environment are supported by the partial reflective observations. Unlike existing inverse-rendering and reflection-aware Gaussian-splatting approaches, which typically require full 360-degree coverage and struggle under incomplete views, PanoLess enables consistent, physically grounded illumination estimation from partial-view input. We show that PanoLess achieves high-fidelity and geometrically consistent environment reconstruction, outperforming reflection-aware baselines on a new custom synthetic benchmark and publicly available datasets, and demonstrating generalization to real-world reflective captures.

Problem

• environment reconstruction
• partial reflections
• illumination estimation
• reflective surfaces
• incomplete views

Innovation

• Gaussian splatting
• reflection-based reconstruction
• neural cubemap
• partial-view illumination
• deferred shading