Papers/2611.23416
🧪 Test?View on arXiv

OCLDA-GS: Object-Centric Local Deformation-Aware Gaussian Streaming

Not provided

3D reconstructionGaussian splattingdynamic scenesobject tracking
2611.23416
Builder Relevance
70%
15h ago

Abstract

OCLDA-GS introduces an object-centric streaming framework for dynamic scene reconstruction that improves the accuracy of Gaussian splatting by addressing object-specific motion and deformation.

Reality Card

Core Claim

OCLDA-GS improves PSNR over previous methods by up to 0.202 dB while reducing mean PSNR drop between refinement timesteps by up to 13.8%.

Method / Result

Improves PSNR by 0.202 dB on Meeting Room dataset.

Limitations

The paper does not specify the authors or provide detailed implementation guidelines, which may hinder reproducibility.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers