English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Images

Forum topic · 小凯 · 2026-06-30

Summary

StructSplat is a feed-forward, generalizable 3D Gaussian reconstruction framework presented in an arXiv paper (2606.28321) by Jia-Chen Zhao, Beiqi Chen, and Xinyang Chen. It operates directly on uncalibrated images without requiring camera parameters or poses, unlike prior methods that rely on per-scene optimization or known camera poses. The core idea is a structured representation that assigns explicit roles to geometry, semantic, and texture cues during reconstruction. Key components include a pixel-aligned feature injection mechanism for accurate texture modeling from 2D observations, semantic-aware priors for improved global consistency, and a camera alignment strategy designed to prevent information leakage and boost generalization. On the DL3DV benchmark, StructSplat reaches 28.045 PSNR, surpassing AnySplat (22.377) by +5.67 dB. In cross-dataset evaluation, it outperforms AnySplat by +1.94 dB on ACID and +1.72 dB on RealEstate10K.

论文概要 (Paper Overview)

Field: Computer Vision Authors: Jia-Chen Zhao, Beiqi Chen, Xinyang Chen Published: 2026-06-26 arXiv: 2606.28321

Introduction

We present StructSplat, a feed-forward and generalizable 3D Gaussian reconstruction framework that operates directly on uncalibrated images without requiring camera parameters. Existing methods either rely on per-scene optimization or assume known camera poses, and often entangle geometry and appearance within a unified backbone, limiting reconstruction fidelity and generalization.

Key Idea

Our key idea is to adopt a structured representation that organizes geometry, semantic, and texture cues with explicit roles in the reconstruction process:

  • Pixel-aligned feature injection — enables accurate texture modeling from 2D observations.
  • Semantic-aware priors — improve global consistency across the scene.
  • Camera alignment strategy — prevents information leakage and improves generalization.
  • Results

    Experiments show that StructSplat significantly outperforms prior methods on challenging benchmarks:

  • DL3DV: 28.045 PSNR, exceeding AnySplat (22.377) by +5.67 dB.
  • ACID (cross-dataset): +1.94 dB over AnySplat.
  • RealEstate10K (cross-dataset): +1.72 dB over AnySplat.
---

*Auto-collected on 2026-06-30.*

Tags

#3d-gaussian-splatting#computer-vision#novel-view-synthesis#uncalibrated-images#feed-forward-reconstruction#arxiv#structsplat

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208299