{"work":{"id":"a1117a19-eb44-4a5b-866c-4918d06fbdd5","openalex_id":null,"doi":null,"arxiv_id":"2509.19297","raw_key":null,"title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","authors":null,"authors_text":"W","year":2025,"venue":"cs.CV","abstract":"Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \\emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is mapped to a 3D Gaussian. We rethink this widely adopted formulation and identify several inherent limitations: it renders the reconstructed 3D models heavily dependent on the number of input views, leads to view-biased density distributions, and introduces alignment errors, particularly when source views contain occlusions or low texture. To address these challenges, we introduce VolSplat, a new multi-view feed-forward paradigm that replaces pixel alignment with voxel-aligned Gaussians. By directly predicting Gaussians from a predicted 3D voxel grid, it overcomes pixel alignment's reliance on error-prone 2D feature matching, ensuring robust multi-view consistency. Furthermore, it enables adaptive control over density based on 3D scene complexity, yielding more faithful Gaussians, improved geometric consistency, and enhanced novel-view rendering quality. Experiments on widely used benchmarks demonstrate that VolSplat achieves state-of-the-art performance, while producing more plausible and view-consistent results. The video results, code and trained models are available on our project page: https://lhmd.top/volsplat.","external_url":"https://arxiv.org/abs/2509.19297","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-04T13:19:51.046437+00:00","pith_arxiv_id":"2509.19297","created_at":"2026-05-10T06:56:47.301105+00:00","updated_at":"2026-07-04T13:19:51.046437+00:00","title_quality_ok":true,"display_title":"V olsplat: Rethinking feed-forward 3d gaussian splatting with voxel-aligned prediction","render_title":"V olsplat: Rethinking feed-forward 3d gaussian splatting with voxel-aligned prediction"},"hub":{"state":{"work_id":"a1117a19-eb44-4a5b-866c-4918d06fbdd5","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":19,"external_cited_by_count":null,"distinct_field_count":1,"first_pith_cited_at":"2025-12-03T17:59:05+00:00","last_pith_cited_at":"2026-07-02T03:00:23+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T19:19:54.447054+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}