Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RDGWGWSJrecord.jsonopen to challenge →
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/.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction
MarineSTD-GS disentangles true underwater scene appearance from video degradations by deriving degraded Gaussian colors from paired intrinsic Gaussians via a physical spatiotemporal model.
-
WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images
WildSplat decouples geometry from appearance in a single feedforward pass to produce appearance-conditioned 3D Gaussian reconstructions from unposed in-the-wild images.
-
Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios
RefineSplat applies entropy-aware adaptive masking and density control to 3DGS to remove color- or semantically ambiguous distractors, validated on a new 18-scene Ambiguous wild dataset with claimed SOTA results.
-
KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis
KC-3DGS adds multi-scale wavelet alignment, kurtosis concentration, and cross-band covariance losses to 3DGS training to reduce oversmoothing and improve perceptual quality in view synthesis.
-
Conflict-Aware Active Perception and Control in 3D Gaussian Splatting Fields via Control Barrier Functions
A unified quadratic program combines control barrier functions from AV@R risk with risk-aware expected information gain for safe active perception in 3DGS fields.
-
3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling
Proposes a physics-based 3D Gaussian framework that disentangles appearance from medium effects for high-quality underwater novel view synthesis and scene restoration.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.