Summary
StructSplat is a feed-forward, generalizable 3D Gaussian reconstruction framework that operates directly on uncalibrated images without requiring camera parameters (arXiv: 2606.28321). Unlike prior approaches that depend on per-scene optimization or known camera poses—and often entangle geometry and appearance in a single backbone—StructSplat adopts a structured representation that assigns explicit roles to geometry, semantics, and texture. It introduces three key components: 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 that prevents information leakage and improves generalization. On the DL3DV benchmark it 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, demonstrating strong state-of-the-art performance on challenging benchmarks.
Paper Overview
- Field: Computer Vision
- Authors: Jia-Chen Zhao, Beiqi Chen, Xinyang Chen
- Published: 2026-06-26
- arXiv: 2606.28321
Abstract
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. Our key idea is to adopt a structured representation that organizes geometry, semantic, and texture cues with explicit roles in the reconstruction process.
Specifically, we introduce:
- A pixel-aligned feature injection mechanism to enable accurate texture modeling from 2D observations
- Semantic-aware priors to improve global consistency
- A camera alignment strategy to prevent information leakage and improve generalization
Experiments show that our method significantly outperforms prior approaches on challenging benchmarks. On DL3DV, our method achieves 28.045 PSNR, exceeding AnySplat (22.377) by +5.67 dB. In cross-dataset evaluation, our method surpasses AnySplat by +1.94 dB on ACID and +1.72 dB on RealEstate10K.
---
*Auto-collected on 2026-06-30*
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/178208310