Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces PanoLess, a novel Gaussian-splat-based framework designed to reconstruct environments using only partial reflective views from shiny surfaces. By leveraging surface-aligned 2D Gaussian splats and deferred shading, PanoLess effectively estimates per-pixel normals and reflection cues, culminating in a neural cubemap representation of the environment. The method significantly outperforms existing techniques in terms of fidelity and geometric consistency, even with limited input data, showcasing its robustness across synthetic benchmarks and real-world scenarios.
PanoLess achieves high-fidelity environment reconstruction from just one side of a reflective surface, challenging the need for full panoramic views.
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.