Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
Not on the map. Why?
Abstract (arXiv)
Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without per-scene optimization, a capability previously out of reach for feed-forward methods, all while using significantly fewer Gaussian primitives. Project page: https://yxlao.github.io/lgtm/
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 37 references that are in the map. First posted on arXiv 26 Mar 2026.
Builds on
34 of 37 references.
References · 34
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
- 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
- 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
- 2024Grounding Image Matching in 3D with MASt3Rcited by 960
- 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
- 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
- 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
- 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
- 2025Continuous 3D Perception Model with Persistent Statecited by 527
- 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
22 more
- 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
- 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
- 20243D Reconstruction with Spatial Memorycited by 269
- 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
- 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
- 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
- 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
- 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
- 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
- 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
- 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
- 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
- 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
- 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 67
- 20243D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexescited by 50
- 2024Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editingcited by 47
- 2024Textured Gaussians for Enhanced 3D Scene Appearance Modelingcited by 40
- 2024GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modelingcited by 30
- 2024BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesiscited by 23
- 2024HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Renderingcited by 16
- 2024SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colorscited by 13
- 2024Gaussian Billboards: Expressive 2D Gaussian Splatting with Texturescited by 13
Built on by
Not cited yet.