Pith. sign in

REVIEW 7 cited by

Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting 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 2407.12306 v2 pith:RDGWGWSJ submitted 2024-07-17 cs.CV

Congrong Xu , Justin Kerr , Angjoo Kanazawa This is my paper · ORCID
classification cs.CV
keywords appearancecollectionssplatfacto-wunconstrainedbackgroundcomparedembeddingsfeatures
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Novel view synthesis from unconstrained in-the-wild image collections remains a significant yet challenging task due to photometric variations and transient occluders that complicate accurate scene reconstruction. Previous methods have approached these issues by integrating per-image appearance features embeddings in Neural Radiance Fields (NeRFs). Although 3D Gaussian Splatting (3DGS) offers faster training and real-time rendering, adapting it for unconstrained image collections is non-trivial due to the substantially different architecture. In this paper, we introduce Splatfacto-W, an approach that integrates per-Gaussian neural color features and per-image appearance embeddings into the rasterization process, along with a spherical harmonics-based background model to represent varying photometric appearances and better depict backgrounds. Our key contributions include latent appearance modeling, efficient transient object handling, and precise background modeling. Splatfacto-W delivers high-quality, real-time novel view synthesis with improved scene consistency in in-the-wild scenarios. Our method improves the Peak Signal-to-Noise Ratio (PSNR) by an average of 5.3 dB compared to 3DGS, enhances training speed by 150 times compared to NeRF-based methods, and achieves a similar rendering speed to 3DGS. Additional video results and code integrated into Nerfstudio are available at https://kevinxu02.github.io/splatfactow/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images

    cs.CV 2026-07 conditional novelty 6.0 of 10

    WildSplat decouples geometry from appearance in a single feedforward pass to produce appearance-conditioned 3D Gaussian reconstructions from unposed in-the-wild images.

  2. Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    RefineSplat removes ambiguous distractors from 3DGS via entropy-aware adaptive masking and density control, releasing an 18-scene Ambiguous wild dataset and reporting SOTA metrics on multiple wild benchmarks.

  3. LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes

    cs.CV 2026-01 conditional novelty 6.0 of 10

    A three-stage pipeline decomposes indoor scene lighting into individually controllable OLAT sources, harmonizes the decomposition across views, and encodes it in 3D Gaussian splatting for real-time per-light editing.

  4. Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset

    cs.CV 2025-06 conditional novelty 6.0 of 10

    This paper releases and benchmarks a 30 km egocentric day-and-night dataset with SLAM poses and TLS ground truth, and shows current NVS and relocalization methods degrade sharply at night.

  5. Gbake: Baking 3D Gaussian Splats into Reflection Probes

    cs.GR 2025-07 conditional novelty 5.0 of 10

    GBake converts 3D Gaussian Splatting scenes into cubemap reflection probes via ray tracing, enabling Unity meshes to show reflections.

  6. 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.

  7. R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections

    cs.CV 2025-05 conditional novelty 5.0 of 10

    R3GS integrates appearance-conditioned hash features, a fine-tuned human-detector visibility map, and a fixed sky sphere into 3D Gaussian Splatting to improve novel view synthesis and relocalization on Phototourism scenes.

Pith tools