AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2605.10239v2
• Date: Mon, 18 May 2026 06:53:40 GMT
• Title: AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting
• Abstract summary: This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS)<n>We design a Frequency-Preserving Adapter that extracts direction-aware high-frequency structural priors from the shallow features of a powerful vision foundation model backbone.<n>Experiments demonstrate that AdaptSplat achieves state-of-the-art feed-forward reconstruction performance on multiple standard benchmarks.
• Score: 10.259254902492978
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply complex, architecture-specific designs on top of the generic pipeline of image feature extraction $\rightarrow$ multi-view interaction $\rightarrow$ feature decoding. However, constrained by the scale bottleneck of 3D training data and the low-pass filtering effect of deep networks, these methods still fall short in cross-domain generalization and high-frequency geometric fidelity. To address these problems, we propose AdaptSplat, which demonstrates that without complex component engineering, introducing a single adapter of only 1.5M parameters into the generic architecture is sufficient to achieve superior performance. Specifically, we design a lightweight Frequency-Preserving Adapter (FPA) that extracts direction-aware high-frequency structural priors from the shallow features of a powerful vision foundation model backbone, and seamlessly integrates them into the generic pipeline via high-frequency positional encodings and adaptive residual modulation. This effectively compensates for the high-frequency attenuation caused by over-smoothing in deep features, improving the fitting accuracy of Gaussian primitives on complex surfaces and sharp boundaries. Extensive experiments demonstrate that AdaptSplat achieves state-of-the-art feed-forward reconstruction performance on multiple standard benchmarks, with stable generalization across domains. Code available at: https://github.com/xmw666/AdaptSplat.

Related papers

• Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting [8.053023331297602]
  3D Gaussian Splatting (3DGS) achieves real-time rendering but struggles to synthesize high-frequency textures.<n>We propose a versatile 2D perceptual wrapper that enhances the rendered outputs of existing 3DGS representations in a content- and view-dependent manner.
  arXiv  Detail & Related papers  (2026-06-10T08:14:47Z)
• REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance [58.94345609736356]
  REFINE is a highly accelerated 3DGS pruning framework centered on a novel rendering-free primitive importance metric.<n>Experiments across multiple benchmark datasets demonstrate that REFINE maintains highly competitive rendering quality.
  arXiv  Detail & Related papers  (2026-06-08T06:16:38Z)
• Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis [48.743921535513635]
  Iterative Gaussian Synopsis is a novel framework for compact and progressive rendering through a top-down "unfolding" scheme.<n>Our approach begins with a full-resolution 3DGS model and iteratively derives coarser LODs using an adaptive, learnable mask-based pruning mechanism.<n>This combination produces a compact yet expressive feature representation, designed to minimize redundancy and support efficient, level-specific adaptation.
  arXiv  Detail & Related papers  (2026-04-13T16:28:35Z)
• SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction [30.66530885236685]
  3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction.<n>We propose SurfelSplat, a feed-forward framework that generates efficient and generalizable pixel-aligned surfel representations from sparse-view images.<n>Our model achieves comparable results with state-of-the-art methods, and predict Gaussian surfels within 1 second, offering a 100x speedup without costly per-scene training.
  arXiv  Detail & Related papers  (2026-04-09T15:34:24Z)
• One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion [57.824020826432815]
  We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images.<n>We design a Dual-Domain Detail Perception Module, which enables handling high-resolution images without being limited by the ViT backbone.<n>We develop a feature-guided diffusion network, which can preserve high-frequency details during the restoration process.
  arXiv  Detail & Related papers  (2026-01-20T17:11:55Z)
• MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation [92.57609195819647]
  MuSASplat is a novel framework that dramatically reduces the computational burden of training pose-free feed-forward 3D Gaussian splats models.<n>Central to our approach is a lightweight Multi-Scale Adapter that enables efficient fine-tuning of ViT-based architectures with only a small fraction of training parameters.
  arXiv  Detail & Related papers  (2025-12-08T04:56:46Z)
• High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network [73.19214585791268]
  This paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacian pyramid decomposition and reconstruction.<n>Specifically, we utilize an image-adaptive 3D LUT that capitalizes on the global tonal characteristics of downsampled images.<n>LLF-LUT++ not only achieves a 2.64 dB improvement in PSNR on the HDR+ dataset, but also further reduces, with 4K resolution images processed in just 13 ms on a single GPU.
  arXiv  Detail & Related papers  (2025-10-13T16:52:32Z)
• MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction [32.14335364083271]
  We present Multi-Baseline Gaussian Splatting (MuGS), a feed-forward approach for novel view synthesis.<n>MuGS effectively handles diverse baseline settings, including sparse input views with both small and large baselines.<n>We demonstrate promising zero-shot performance on the LLFF and Mip-NeRF 360 datasets.
  arXiv  Detail & Related papers  (2025-08-06T10:34:24Z)
• GBR: Generative Bundle Refinement for High-fidelity Gaussian Splatting with Enhanced Mesh Reconstruction [27.747748706297497]
  We propose GBR: Generative Bundle Refinement, a method for high-fidelity Gaussian splatting and meshing using only 4-6 input views.<n>GBR integrates a neural bundle adjustment module to enhance geometry accuracy and a generative depth refinement module to improve geometry fidelity.<n>GBR demonstrates the ability to reconstruct and render large-scale real-world scenes, with remarkable details using only 6 views.
  arXiv  Detail & Related papers  (2024-12-08T12:00:25Z)
• GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering [69.67264955234494]
  GeoSplatting is a novel approach that augments 3DGS with explicit geometry guidance for precise light transport modeling.<n>By differentiably constructing a surface-grounded 3DGS from an optimizable mesh, our approach leverages well-defined mesh normals and the opaque mesh surface.<n>This enhancement ensures precise material decomposition while preserving the efficiency and high-quality rendering capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-31T17:57:07Z)
• FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization [73.41395947275473]
  We propose a novel frequency-aware architecture, in which the domain-specific features are filtered out in the transformed frequency domain. Experiments on three benchmarks demonstrate significant performance, outperforming the state-of-the-art methods by a margin of 3%, 4% and 9%, respectively.
  arXiv  Detail & Related papers  (2022-03-24T07:26:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.