Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors

About

Recent advances in novel view synthesis (NVS) have enabled real-time rendering with 3D Gaussian Splatting (3DGS). However, existing methods struggle with artifacts and missing regions when rendering from viewpoints that deviate from the training trajectory, limiting seamless scene exploration. To address this, we propose a 3DGS-based pipeline that generates additional training views to enhance reconstruction. We introduce an information-gain-driven virtual camera placement strategy to maximize scene coverage, followed by video diffusion priors to refine rendered results. Fine-tuning 3D Gaussians with these enhanced views significantly improves reconstruction quality. To evaluate our method, we present Wild-Explore, a benchmark designed for challenging scene exploration. Experiments demonstrate that our approach outperforms existing 3DGS-based methods, enabling high-quality, artifact-free rendering from arbitrary viewpoints. https://exploregs.github.io

Minsu Kim, Subin Jeon, In Cho, Mijin Yoo, Seon Joo Kim• 2025

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisRe10K (test)
PSNR24.025
79
Novel View SynthesisDL3DV (test)
PSNR20.689
61
3D Scene ReconstructionRe10K (test)
LPIPS25.7
15
3D Scene ReconstructionDL3DV (test)
LPIPS0.377
14
Novel View SynthesisRE10K official (test)
PSNR21.195
9
Showing 5 of 5 rows

Other info

Follow for update