{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:43:57Z","timestamp":1773801837673,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Reconstructing a faithful geometric surface from sparse images remains a fundamental challenge in 3D computer vision. While recent methods have achieved remarkable progress, they still struggle to recover reliable geometry due to the lack of multi-view geometric cues, particularly in non-overlapping regions. To address this issue, we introduce VGGS, a Gaussian Splatting (GS) method that exploits multi-view geometric priors from VGGT for efficient and high-fidelity sparse-view surface reconstruction. Our primary contribution is an anchor-calibrated depth estimation scheme, which yields accurate depth maps. The insight is to align the VGGT depth prior to the underlying surface with a sparse set of multi-view consistent anchors, then infer depth for unreliable regions by relative depth estimation. Furthermore, to mitigate misalignment in complex scenes, we propose a relative depth consistency loss that penalizes the rendered depth if its relative depth relationship in local regions is inconsistent to the multi-view prior. Extensive experiments on widely-used benchmarks show that VGGS surpasses state-of-the-art methods in both accuracy and efficiency, delivering 4\u20137\u00d7 faster optimization while reducing memory consumption compared to previous GS-based approaches.<\/jats:p>","DOI":"10.1609\/aaai.v40i13.38074","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:02:25Z","timestamp":1773792145000},"page":"10969-10977","source":"Crossref","is-referenced-by-count":0,"title":["VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction"],"prefix":"10.1609","volume":"40","author":[{"given":"Peng","family":"Xiang","sequence":"first","affiliation":[]},{"given":"Liang","family":"Han","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yu-Shen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhizhong","family":"Han","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38074\/42036","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38074\/42036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:02:25Z","timestamp":1773792145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38074"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i13.38074","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}