{"ID":2828728,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.12898","arxiv_id":"2512.12898","title":"Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks","abstract":"Gaussian Splatting has revolutionized the field of Novel View Synthesis (NVS) with faster training and real-time rendering. However, its reconstruction fidelity still trails behind the powerful radiance models such as Zip-NeRF. Motivated by our theoretical result that both queries (such as coordinates) and neighborhood are important to learn high-fidelity signals, this paper proposes Queried-Convolutions (Qonvolutions), a simple yet powerful modification using the neighborhood properties of convolution. Qonvolutions convolve a low-fidelity signal with queries to output residual and achieve high-fidelity reconstruction. We empirically demonstrate that combining Gaussian splatting with Qonvolution neural networks (QNNs) results in state-of-the-art NVS on real-world scenes, even outperforming Zip-NeRF on image fidelity. QNNs also enhance performance of 1D regression, 2D regression and 2D super-resolution tasks.","short_abstract":"Gaussian Splatting has revolutionized the field of Novel View Synthesis (NVS) with faster training and real-time rendering. However, its reconstruction fidelity still trails behind the powerful radiance models such as Zip-NeRF. Motivated by our theoretical result that both queries (such as coordinates) and neighborhood...","url_abs":"https://arxiv.org/abs/2512.12898","url_pdf":"https://arxiv.org/pdf/2512.12898v2","authors":"[\"Abhinav Kumar\",\"Tristan Aumentado-Armstrong\",\"Lazar Valkov\",\"Gopal Sharma\",\"Alex Levinshtein\",\"Radek Grzeszczuk\",\"Suren Kumar\"]","published":"2025-12-15T00:46:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\",\"cs.LG\"]","methods":"[]","has_code":false}