GlobalSplat achieves competitive novel-view synthesis on RealEstate10K and ACID using only 16K Gaussians via global scene tokens and coarse-to-fine training, with a 4MB footprint and under 78ms inference.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 5years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Video diffusion models can be adapted into permutation-invariant generators for sparse novel view synthesis by treating the problem as video completion and removing temporal order cues.
FluSplat trains a model with geometric alignment constraints on multi-view edits to produce consistent 3D scene edits from sparse views in a single forward pass without test-time optimization.
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
TouchAnything reconstructs accurate 3D object geometries from only a few tactile contacts by optimizing for consistency with a pretrained visual diffusion prior.
citing papers explorer
-
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
GlobalSplat achieves competitive novel-view synthesis on RealEstate10K and ACID using only 16K Gaussians via global scene tokens and coarse-to-fine training, with a 4MB footprint and under 78ms inference.
-
Novel View Synthesis as Video Completion
Video diffusion models can be adapted into permutation-invariant generators for sparse novel view synthesis by treating the problem as video completion and removing temporal order cues.
-
FluSplat: Sparse-View 3D Editing without Test-Time Optimization
FluSplat trains a model with geometric alignment constraints on multi-view edits to produce consistent 3D scene edits from sparse views in a single forward pass without test-time optimization.
-
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
-
TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches
TouchAnything reconstructs accurate 3D object geometries from only a few tactile contacts by optimizing for consistency with a pretrained visual diffusion prior.