Papers/2609.28645
🧪 Test?View on arXiv

PePESeg3D: Perception Prior Enhances Multi-Scale Segmentation for 3D Gaussian Splatting

BeCow5X5, Author2, Author3, Author4, Author5

3D segmentationGaussian Splattingperception priorsfeature learning
2609.28645
Builder Relevance
80%
1h ago

Abstract

PePESeg3D introduces a novel framework that integrates perception priors into multi-scale 3D Gaussian segmentation, enhancing both geometry reconstruction and feature learning.

Reality Card

Core Claim

PePESeg3D achieves state-of-the-art performance in multi-scale segmentation and scene reconstruction by effectively integrating perception priors into both geometry optimization and feature learning.

Method / Result

Achieves state-of-the-art performance on SPIn-NeRF, LERF-Mask, and NVOS benchmarks.

Limitations

The reliance on incomplete mask supervision may affect the generalizability of the results.

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