InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Hugging Face Daily Papers Papers
3d-gaussian-splatting monocular-view-synthesis feed-forward implicit-decoding depth-guided computer-vision

Summary

InfiniSplat presents a feed-forward single-image 3D Gaussian Splatting framework that uses geometry-guided sampling and query-conditioned implicit decoding to achieve surface-aligned Gaussian representation, improving large-baseline monocular view synthesis and generalizing from synthetic indoor training to open-world scenes.

Single-image feed-forward 3D Gaussian Splatting (3DGS) aims to directly generate a renderable 3D scene representation from one input image, avoiding the cost of multi-view capture and per-scene optimization. However, existing methods are often constrained by a pixel-aligned representation, where Gaussians are predicted from fixed image-grid locations. Such pixel-aligned primitives can produce promising nearby-view renderings, but they remain weakly coupled to underlying scene surfaces and struggle to preserve coherent structures under large viewpoint shifts. We present InfiniSplat, a feed-forward single-image 3DGS framework that moves from a pixel-aligned representation toward a surface-aligned representation. InfiniSplat constructs this representation by first using geometry-guided sampling to place 2D supports according to depth-induced local surface structure, and then applying a query-conditioned implicit decoder to predict Gaussian attributes from the image features queried at these supports.By grounding support locations in geometry while decoupling Gaussian prediction from fixed pixel centers, InfiniSplat produces Gaussian layouts that better follow scene surfaces and reduce scattered primitives caused by grid discretization.Across multiple cross-dataset NVS evaluations, InfiniSplat achieves state-of-the-art performance compared with single-image feed-forward baselines, and demonstrates zero-shot generalization from Hypersim indoor synthetic training to complex open-world scenes.Project page: https://zju3dv.github.io/InfiniSplat.
Original Article
View Cached Full Text

Cached at: 08/05/26, 01:42 AM

Paper page - InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Source: https://huggingface.co/papers/2608.02437

Abstract

Single-imagefeed-forward3DGaussianSplatting(3DGS)aimstodirectlygeneratearenderable3Dscenerepresentationfromoneinputimage,avoidingthecostofmulti-viewcaptureandper-sceneoptimization.However,existingmethodsareoftenconstrainedbyapixel-alignedrepresentation,whereGaussiansarepredictedfromfixedimage-gridlocations.Suchpixel-alignedprimitivescanproducepromisingnearby-viewrenderings,buttheyremainweaklycoupledtounderlyingscenesurfacesandstruggletopreservecoherentstructuresunderlargeviewpointshifts.WepresentInfiniSplat,afeed-forwardsingle-image3DGSframeworkthatmovesfromapixel-alignedrepresentationtowardasurface-alignedrepresentation.InfiniSplatconstructsthisrepresentationbyfirstusinggeometry-guidedsamplingtoplace2Dsupportsaccordingtodepth-inducedlocalsurfacestructure,andthenapplyingaquery-conditionedimplicitdecodertopredictGaussianattributesfromtheimagefeaturesqueriedatthesesupports.BygroundingsupportlocationsingeometrywhiledecouplingGaussianpredictionfromfixedpixelcenters,InfiniSplatproducesGaussianlayoutsthatbetterfollowscenesurfacesandreducescatteredprimitivescausedbygriddiscretization.Acrossmultiplecross-datasetNVSevaluations,InfiniSplatachievesstate-of-the-artperformancecomparedwithsingle-imagefeed-forwardbaselines,anddemonstrateszero-shotgeneralizationfromHypersimindoorsynthetictrainingtocomplexopen-worldscenes.Projectpage:https://zju3dv.github.io/InfiniSplat.

View arXiv pageView PDFProject pageGitHub105Add to collection

Get this paper in your agent:

hf papers read 2608\.02437

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### PLUS-WAVE/InfiniSplat Image-to-3D• Updatedabout 1 hour ago • 6

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.02437 in a dataset README.md to link it from this page.

Spaces citing this paper2

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Hugging Face Daily Papers

GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.

SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

Hugging Face Daily Papers

SplatWeaver is a feed-forward novel view synthesis framework that dynamically allocates 3D Gaussian primitives based on spatial complexity, improving rendering quality and efficiency over fixed-allocation methods. It leverages cardinality Gaussian experts and a pixel-level routing scheme guided by high-frequency priors to adaptively distribute primitives across complex and smooth scene regions.

ZipSplat: Fewer Gaussians, Better Splats

Hugging Face Daily Papers

ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.