{"ID":2836269,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21113","arxiv_id":"2511.21113","title":"FaithFusion: Harmonizing Reconstruction and Generation via Pixel-wise Information Gain","abstract":"In controllable driving-scene reconstruction and 3D scene generation, maintaining geometric fidelity while synthesizing visually plausible appearance under large viewpoint shifts is crucial. However, effective fusion of geometry-based 3DGS and appearance-driven diffusion models faces inherent challenges, as the absence of pixel-wise, 3D-consistent editing criteria often leads to over-restoration and geometric drift. To address these issues, we introduce \\textbf{FaithFusion}, a 3DGS-diffusion fusion framework driven by pixel-wise Expected Information Gain (EIG). EIG acts as a unified policy for coherent spatio-temporal synthesis: it guides diffusion as a spatial prior to refine high-uncertainty regions, while its pixel-level weighting distills the edits back into 3DGS. The resulting plug-and-play system is free from extra prior conditions and structural modifications.Extensive experiments on the Waymo dataset demonstrate that our approach attains SOTA performance across NTA-IoU, NTL-IoU, and FID, maintaining an FID of 107.47 even at 6 meters lane shift. Our code is available at https://github.com/wangyuanbiubiubiu/FaithFusion.","short_abstract":"In controllable driving-scene reconstruction and 3D scene generation, maintaining geometric fidelity while synthesizing visually plausible appearance under large viewpoint shifts is crucial. However, effective fusion of geometry-based 3DGS and appearance-driven diffusion models faces inherent challenges, as the absence...","url_abs":"https://arxiv.org/abs/2511.21113","url_pdf":"https://arxiv.org/pdf/2511.21113v1","authors":"[\"YuAn Wang\",\"Xiaofan Li\",\"Chi Huang\",\"Wenhao Zhang\",\"Hao Li\",\"Bosheng Wang\",\"Xun Sun\",\"Jun Wang\"]","published":"2025-11-26T06:58:57Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":606585,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2836269,"paper_url":"https://arxiv.org/abs/2511.21113","paper_title":"FaithFusion: Harmonizing Reconstruction and Generation via Pixel-wise Information Gain","repo_url":"https://github.com/wangyuanbiubiubiu/FaithFusion","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}