GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting

• URL: http://arxiv.org/abs/2607.00595v2
• Date: Thu, 02 Jul 2026 10:30:41 GMT
• Title: GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
• Abstract summary: Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques.<n>However, such methods suffer from pixel-level inaccuracies due to uncertain geometry.<n>This uncertainty leads to spatial misalignments in the warped images, which disrupt residual learning.<n>We propose Geometry-Aware Deformable Aggregation (GADA) to actively correct spatial misalignments and recover displaced cues.
• Score: 40.87793066043428
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques. However, such methods suffer from pixel-level inaccuracies due to uncertain geometry. This uncertainty leads to spatial misalignments in the warped images, which disrupt residual learning used in warping-based methods and fundamentally limit the gains of correction, particularly on thin structures and high-frequency details. Driven by our insight that useful visual cues are not lost but locally preserved under slight displacement, we propose Geometry-Aware Deformable Aggregation (GADA). This method introduces an iterative refinement module with deformable offsets to actively correct spatial misalignments and recover these displaced cues. Furthermore, to address the limitations of standard pipelines where visibility checks (i.e., thresholding) often discard valid pixels and multi-view warped image fusion relies on naive mean aggregation, our module is coupled with an implicit confidence weighting mechanism that selectively suppresses unreliable evidence. Consequently, our approach outperforms prior warping-based Gaussian Splatting, preserving high-frequency quality while achieving 2.13 times faster FPS.

Related papers

• Pixel-Space Diffusion via Observation Operators [22.391778551506345]
  We propose a unified framework that aligns full-image supervision and feature refinement with the intrinsic recovery order of image structures.<n>Experiments show that the proposed approach converges substantially faster while consistently improving generation quality, achieving an FID of 1.52 on ImageNet-256.
  arXiv  Detail & Related papers  (2026-08-22T09:54:01Z)
• Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image Restoration [15.371827475537776]
  Local Epistemic Uncertainty Guided Active Sampling framework is developed.<n>It balances detail preservation and artifact suppression in the spatial domain.<n>It reduces sampling time with negligible memory overhead.
  arXiv  Detail & Related papers  (2026-08-07T09:00:20Z)
• A Unified Variational Framework for Deep Weakly Supervised Image Segmentation [6.232598868087682]
  We propose a unified variational framework for image segmentation under sparse pixel-level supervision.<n>Our method is based on a simplex-constrained Potts model with a smooth perimeter regularizer.<n>Sparse labels are incorporated into the data fidelity term by constructing a fuzzy membership function.
  arXiv  Detail & Related papers  (2026-07-22T02:18:15Z)
• Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation [3.881211374324378]
  Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.<n>We propose a gradient-free methodology reframing detection from binary classification to an out-of-distribution (OOD) anomaly measurement problem.
  arXiv  Detail & Related papers  (2026-06-03T13:04:23Z)
• HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization [82.42818558196615]
  In-the-wild 3D Gaussian Splatting remains challenging due to transient distractors and illumination-induced cross-view appearance inconsistencies.<n>We propose a conflict-aware 3DGS framework that addresses this problem from both image-space supervision and gradient-level optimization.<n>Our method achieves state-of-the-art rendering quality under complex transient distractors and cross-view inconsistencies.
  arXiv  Detail & Related papers  (2026-05-13T06:47:09Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• Robust Perspective Correction for Real-World Crack Evolution Tracking in Image-Based Structural Health Monitoring [0.2525107441836083]
  This study presents a physics-informed alignment framework that adapts the open KAZE architecture to SHM-specific challenges.<n>Compared to classical detectors, the proposed framework reduces crack area and spine length errors by up to 70 percent and 90 percent, respectively.<n>Unsupervised, interpretable, and computationally lightweight, this approach supports scalable deployment via UAVs and mobile platforms.
  arXiv  Detail & Related papers  (2025-05-06T07:25:33Z)
• Robust Steganography with Boundary-Preserving Overflow Alleviation and Adaptive Error Correction [14.517951900805317]
  Existing methods aim to ensure the stability of the quantized coefficients by reducing the effects of spatial truncation. Existing methods may induce notable alterations to image pixels, potentially compromising anti-steganalysis performance. We propose a preprocessing method that performs overflow removal operations based on the actual overflow conditions of spatial blocks.
  arXiv  Detail & Related papers  (2024-11-21T03:49:18Z)
• Parallax-Tolerant Unsupervised Deep Image Stitching [57.76737888499145]
  We propose UDIS++, a parallax-tolerant unsupervised deep image stitching technique. First, we propose a robust and flexible warp to model the image registration from global homography to local thin-plate spline motion. To further eliminate the parallax artifacts, we propose to composite the stitched image seamlessly by unsupervised learning for seam-driven composition masks.
  arXiv  Detail & Related papers  (2023-02-16T10:40:55Z)
• Deblurring via Stochastic Refinement [85.42730934561101]
  We present an alternative framework for blind deblurring based on conditional diffusion models. Our method is competitive in terms of distortion metrics such as PSNR.
  arXiv  Detail & Related papers  (2021-12-05T04:36:09Z)

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.