FinerSplat: Distilling Diffusion Priors for Feed-Forward Gaussian Refinement

Feed-forward 3D Gaussian Splatting (3DGS) enables efficient reconstruction from sparse views, yet its single-pass prediction must determine both Gaussian attributes and primitive allocation without rendering feedback, often producing inaccurate and redundant primitives in under-constrained regions. Although generative priors can improve rendered images, transferring them into 3D Gaussian representations often requires costly per-scene optimization. We present FinerSplat, a feed-forward framework that casts refinement and compaction as coupled primitive-level decisions without per-scene optimization. It restores target-view renderings with a frozen diffusion model and lifts the resulting residuals into Gaussian-level observations through differentiable rendering contributions. An entropy-aware primitive-level Transformer predicts recurrent attribute updates and primitive-wise keep scores from these observations. Experiments on DL3DV and Waymo demonstrate that FinerSplat performs feed-forward refinement in 0.6 s and removes 30% of the initialized Gaussians while preserving rendering quality.