Splatfacto-W is an implementation of Gaussian Splatting in Nerfstudio, designed to handle unconstrained photo collections for novel view synthesis. The method 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 improve background depiction. 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, achieving a 5.3 dB average increase in Peak Signal-to-Noise Ratio (PSNR) compared to 3D Gaussian Splatting (3DGS), enhancing training speed by 150 times compared to NeRF-based methods, and maintaining similar rendering speed to 3DGS. The method effectively handles diverse lighting conditions and transient occluders, providing more consistent and high-quality scene reconstructions. Additional video results and code are available on the project's website.Splatfacto-W is an implementation of Gaussian Splatting in Nerfstudio, designed to handle unconstrained photo collections for novel view synthesis. The method 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 improve background depiction. 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, achieving a 5.3 dB average increase in Peak Signal-to-Noise Ratio (PSNR) compared to 3D Gaussian Splatting (3DGS), enhancing training speed by 150 times compared to NeRF-based methods, and maintaining similar rendering speed to 3DGS. The method effectively handles diverse lighting conditions and transient occluders, providing more consistent and high-quality scene reconstructions. Additional video results and code are available on the project's website.