GrapeSplat amalgamates multi-view cues into a voxel-aligned scene representation and decodes Gaussians directly from the learned grid, requiring no per-scene optimization or post-processing.
Abstract
Feed-forward 3D Gaussian Splatting now reconstructs renderable scenes from unposed, uncalibrated images. Yet, most models supervise only photometric consistency and predict Gaussians pixel by pixel, which leaves global structure fragile and ties primitive count to image resolution and view count. To this end, GrapeSplat amalgamates multi-view cues into a voxel-aligned scene representation and decodes Gaussians directly from the learned grid, requiring no per-scene optimization or post-processing. An Atlas Encoder lifts all views into pixel-wise geometry-and-appearance features anchored at predicted 3D points. PEACH-Vox compands the unbounded scene into a bounded sparse grid through a smooth per-axis map with an exact closed-form inverse. The Sparse Decoder then consolidates the grid with sparse convolutions and decodes the full scene as multiple Gaussians per occupied cell. This amalgamated representation exploits sparse voxel occupancy, where the Gaussian count follows the occupied cells and saturates as views cover the scene, while grid resolution sets its ceiling. GrapeSplat turns unposed images into a renderable Gaussian scene in a single forward pass. Trained with 2D and 3D supervision on 8-view sequences, it generalizes zero-shot from 4 to 64 views across indoor and unbounded scenes. Code and trained weights are available at https://github.com/VAISR/GrapeSplat
DeltaSplat, a lightweight Gaussian refinement module for pose-free feed-forward 3DGS, improves its state-of-the-art backbone by 1.75 dB and surpassing even baselines supplied with ground-truth cameras; consistent gains hold across 6-24 views and all camera regimes.
Chanung Park, Seunghyeon Song, J. Lee et al.· 0 citations
AnyGS2Mesh is presented, the first feed-forward framework for directly reconstructing 3D meshes from 3D Gaussian Splatting representations with support for arbitrary input image resolutions, and demonstrates the potential of combining Gaussian representations and feed-forward Transformer architectures for scalable 3D g...
Yuxuan Song, Fan Gao, Yi-Bo Zhao et al.· 0 citations
Recent feed-forward 3D Gaussian Splatting (3DGS) methods typically regress pixel-aligned Gaussian primitives, often causing excessive overlap and artifacts, while inaccuracies in predicted camera poses can lead to misalignment in novel-view synthesis (NVS). We present VoxelTTO, a feed-forward framework for reconstructi...
Yi-Bin Zhao, Yi-Han Pan, Yang Li et al.· arXiv.org· 0 citations
Across RealEstate10K, DL3DV, Tanks-and-Temples, and Mip-NeRF 360, SplatGuide achieves state-of-the-art pose-free novel view synthesis, and surpasses the ground-truth-pose baseline.
Ye-Jun Zhang, Zi-Han Wang, Xue-Si Ji et al.· 0 citations
GaussianDS, a depth-supervised semantic 3DGS framework that treats semantic lifting as a supervision-alignment problem and jointly optimizes RGB appearance, rendered depth, and compact semantics from scratch, is proposed.
This work presents AVSplat, a framework that turns additional views into reliable signals for both aggregation and representation, and restores positive view scaling where performance remains stable or improves as more input views are added, instead of degrading in the dense-view regime.
Muyu Xu, Fang-Neng Zhan, Yu Wei et al.· 0 citations
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.