{"ID":5937673,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T12:06:23.197441916Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04256","arxiv_id":"2607.04256","title":"AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction","abstract":"Current feed-forward 3D reconstruction methods predict pixel aligned Gaussian primitives, resulting in highly redundant representations. A natural solution is to prune the redundant Gaussians, but naive pruning introduces severe artifacts and often requires inference time fine-tuning, breaking the feed-forward paradigm. Based on previous works, high frequency regions require more Gaussian primitives, while low frequency regions can be represented with significantly fewer primitives. Motivated by this, we propose a novel approach to explicitly control the number of Gaussians by leveraging local texture information. Our approach achieves this through three key components: (1) texture estimation to capture spatial variation in scene detail, (2) texture-aware pruning that removes redundant Gaussians from low frequency regions, and (3) an adaptive Gaussian head that predicts the modified attributes of the retained primitives without breaking the feed-forward paradigm. Experiments on RE10K, ACID, DL3DV, Tanks and Temples, and DTU demonstrate the effectiveness of our approach, while ablation studies validate the contributions of its key components.","short_abstract":"Current feed-forward 3D reconstruction methods predict pixel aligned Gaussian primitives, resulting in highly redundant representations. A natural solution is to prune the redundant Gaussians, but naive pruning introduces severe artifacts and often requires inference time fine-tuning, breaking the feed-forward paradigm...","url_abs":"https://arxiv.org/abs/2607.04256","url_pdf":"https://arxiv.org/pdf/2607.04256v1","authors":"[\"Badrinath Singhal\",\"Srihari K G\",\"Sreehari Iyer\",\"Ankit Dhiman\",\"Venkatesh Babu Radhakrishnan\"]","published":"2026-07-05T12:12:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}