Pith. sign in

REVIEW 9 cited by

WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.02407 v1 pith:7PVWTSP7 submitted 2024-06-04 cs.CV

Yuze Wang , Junyi Wang , Yue Qi This is my paper · ORCID
classification cs.CV
keywords collectionsphotorenderingappearanceefficientgaussianmoduleunconstrained
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Novel View Synthesis (NVS) from unconstrained photo collections is challenging in computer graphics. Recently, 3D Gaussian Splatting (3DGS) has shown promise for photorealistic and real-time NVS of static scenes. Building on 3DGS, we propose an efficient point-based differentiable rendering framework for scene reconstruction from photo collections. Our key innovation is a residual-based spherical harmonic coefficients transfer module that adapts 3DGS to varying lighting conditions and photometric post-processing. This lightweight module can be pre-computed and ensures efficient gradient propagation from rendered images to 3D Gaussian attributes. Additionally, we observe that the appearance encoder and the transient mask predictor, the two most critical parts of NVS from unconstrained photo collections, can be mutually beneficial. We introduce a plug-and-play lightweight spatial attention module to simultaneously predict transient occluders and latent appearance representation for each image. After training and preprocessing, our method aligns with the standard 3DGS format and rendering pipeline, facilitating seamlessly integration into various 3DGS applications. Extensive experiments on diverse datasets show our approach outperforms existing approaches on the rendering quality of novel view and appearance synthesis with high converge and rendering speed.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SimVS: Simulating World Inconsistencies for Robust View Synthesis

    cs.CV 2024-12 conditional novelty 7.0 of 10

    Video diffusion models simulate world inconsistencies, and a harmonization network trained on the simulated data reconciles sparse inconsistent multi-view images into consistent 3D scenes.

  2. ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes

    cs.GR 2025-11 conditional novelty 6.0 of 10

    A single shared Gaussian scaffold with per-period features and opacity gating reconstructs multi-period scenes better than static and dynamic baselines on a new 12-scene benchmark.

  3. Micro-macro Gaussian Splatting with Enhanced Scalability for Unconstrained Scene Reconstruction

    cs.CV 2025-06 conditional novelty 6.0 of 10

    SMW-GS improves unconstrained and large-scale 3D reconstruction by combining micro-macro frustum sampling, wavelet-based frequency features, and visibility-aware camera partitioning.

  4. Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images

    cs.CV 2025-01 conditional novelty 6.0 of 10

    MW-GS improves unconstrained-photo 3D reconstruction with jittered micro/macro frustum sampling and wavelet-based multi-scale features, reporting about 1.2 to 1.4 dB PSNR gains over GS-W.

  5. Impact of Solar Particle Events on Space Radiation Shielding: OLTARIS Simulation and Quantum Optimization of Material Selection using QAOA and VQE Algorithms

    physics.med-ph 2025-08 reject novelty 5.0 of 10

    The abstract claims quantum-optimized shielding material selection, but the full text is an unrelated 3D Gaussian Splatting paper, so the claim is unsupported.

  6. Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Seg-Wild performs interactive 3D segmentation on Gaussian Splatting reconstructions of unconstrained photo collections by embedding SAM features, adaptively sampling SAM prompts by depth, and trimming spiky Gaussians.

  7. RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS

    cs.CV 2025-06 conditional novelty 5.0 of 10

    RobustSplat improves transient-free 3D Gaussian Splatting by postponing densification to 10,000 iterations and bootstrapping mask supervision from low to high resolution.

  8. Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs

    cs.CV 2025-04 conditional novelty 5.0 of 10

    A training-free superpoint graph on 3D Gaussians enables fast, view-consistent, hierarchical open-vocabulary segmentation, reportedly cutting semantic field construction time by over 30x.

  9. NexusSplats: Efficient 3D Gaussian Splatting in the Wild

    cs.CV 2024-11 conditional novelty 5.0 of 10

    NexusSplats replaces per-Gaussian appearance codes with kernel-level shared codes and 3D uncertainty propagation, achieving comparable rendering quality with 65.4% fewer parameters and 2.7x faster training.

Pith tools