All research

Research · Thread 03

Mirrors and glass capture

The open problem Gaussian Splatting still hasn't solved for high-end interiors.

Splatting reconstructs surfaces from photographs, but a mirror or a floor-to-ceiling glass wall is a reflection rather than a surface, so pipelines either ghost the reflected room into the wrong volume or hollow out the geometry behind the glass. In luxury real estate, where mirrors and glass walls are everywhere, that is the bottleneck rather than an edge case. The primary bet is handling it when the scene is captured rather than in the renderer; a render-side reflection branch is being explored in parallel, early and unproven, with nothing measured yet.

Findings

Paper to shipped

  1. Reference

    MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections (Liu, Tang, Cheng, Yang, Li, Liu, ECCV 2024)

    A leading attempt at handling mirrors in 3DGS by jointly modelling the real and reflected geometry. Promising on benchmarks; not yet plug-and-play for production capture.

    View abstract
    The key insight is that a mirrored scene is symmetric to the real scene with respect to the mirror plane. Building on this, the authors introduce a dual-rendering strategy that models the real-world and the mirror-world simultaneously, with an intersection-aware mirror Gaussian formulation that handles partial reflections. Demonstrated on real-world scenes containing mirrors with state-of-the-art reconstruction quality vs. prior 3DGS variants.
  2. Left open

    Capture-side mitigation pipeline

    Inside the benchmark, the per-engine failure analysis names mirrors / glass / chrome as the dominant artefact class on the Hard tier. The primary mitigation candidates are at the photogrammetry layer (mask + inpaint pre-COLMAP, dual-pass capture, controlled-lighting subsets); in parallel, a render-side reflection branch is an early exploration on a real reflective showroom scan, with no run log or measured result behind it yet.

  3. Paper

    Reflection-Aware 5DGS (unsubmitted)

    The render-side companion paper: classified-quadric reflectors proposed for the mirror-and-glass problem in specular interiors. Four pages, anonymised for double-blind review, audited for citation and claim accuracy. Complete but unsubmitted, past the 27 July 2026 SIGGRAPH Asia 2026 deadline.

Contact

Pavlo Puzikov, a black and white studio portrait in a pinstripe suit.

Pavlo Puzikov

Marketing and innovation: immersive 3D, applied AI, generative content

Write to

pavlopuzikov@gmail.com

Open to
Freelance projects, remote. Full-time roles, onsite or hybrid in the EU.
Based in
Bulgaria
Most recent role
Marketing and Innovation Lead, BARNES Dubai, 2026. Product Innovation Researcher there from 2025.
Education
BCom, Marketing and Management, University of Auckland, 2020 to 2023
Languages
English, Russian