Learning to Adaptively Allocate Gaussians for Arbitrary-Scale Image Super-Resolution

• URL: http://arxiv.org/abs/2606.29400v1
• Date: Sun, 28 Jun 2026 13:47:43 GMT
• Title: Learning to Adaptively Allocate Gaussians for Arbitrary-Scale Image Super-Resolution
• Abstract summary: In computer graphics, visual content is continuously warped, zoomed and resampled.<n> Handling these transformations requires Arbitrary-Scale Super-Resolution (ASR)<n>Traditional models, designed for fixed scales, typically predict at a lower integer scale and rely on sub-optimal for continuous resolutions.
• Score: 8.784098322731909
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In computer graphics, visual content is continuously warped, zoomed and resampled. This occurs when engines upscale frames, users zoom into 3D scenes, or foveated VR applies varying scaling. Handling these transformations requires Arbitrary-Scale Super-Resolution (ASR). Traditional models, designed for fixed scales, typically predict at a lower integer scale (e.g., x4) and rely on sub-optimal interpolation for continuous resolutions, compromising quality. Furthermore, most methods process pixels uniformly. Since fine details are sparse, this creates overhead; efficiency dictates concentrating resources only where structural complexity demands it. While implicit models and Gaussian Splatting (GS) enable continuous representation, GS is advantageous due to adaptive densification. However, transitioning GS into a feed-forward model for ASR is non-trivial. Standard GS optimization needs high-resolution gradients to drive primitive growth, which are unavailable during inference. Thus, the network must autonomously predict GS densification from low-resolution inputs. To solve this, we propose QuADA-GS. After encoding inputs into a latent space, a Neural Routing Architecture evaluates local complexity to distribute a global budget, assigning specific upsampling factors to features to avoid redundant processing. Features are dynamically densified based on these factors, forming an irregular topology decoded into 2D Gaussian primitives. To coordinate features before decoding, we introduce Hierarchical Pointer Convolution. This non-grid operator achieves O(1) neighbor lookup complexity, facilitating efficient spatial communication and bypassing dense bottlenecks. Experiments show QuADA-GS achieves state-of-the-art ASR performance, maintaining low latency and a lean memory footprint.

Related papers

• MMGS: 10$\ imes$ Compressed 3DGS through Optimal Transport Aggregation based on Multi-view Ranking [6.445070918236315]
  We propose a novel framework that formulates Gaussian optimization as a global geometric distribution matching problem.<n>Our approach achieves state-of-the-art rendering quality with only textbf10$%$ primitives and textbf10$times$ accelerated training speeds compared to vanilla 3DGS.
  arXiv  Detail & Related papers  (2026-05-19T03:33:02Z)
• Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification [52.517763621139956]
  3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis.<n>Standard adaptive density control relies on screen-space positional gradients.<n>We present a structure-aware densification framework for 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-30T15:37:20Z)
• NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation [65.34304674634713]
  We introduce NG-GS, a framework for high-quality object segmentation in 3DGS that explicitly addresses boundary discretization.<n>We show that our method achieves photorealistic state-of-the-art performance, with significant gains in boundary mIoU.
  arXiv  Detail & Related papers  (2026-04-16T07:14:07Z)
• GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting [50.2045409672451]
  3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering.<n>It is constrained by the high memory cost due to a huge number of Gaussian points.<n>We propose graph-based spatial distribution optimization for compact 3DGS.
  arXiv  Detail & Related papers  (2026-04-02T10:41:51Z)
• Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior [21.89104780995278]
  Fast-2DGS is a lightweight framework for efficient Gaussian image representation.<n>We introduce Deep Gaussian Prior, implemented as a conditional network to capture the spatial distribution of Gaussian primitives.<n> Experiments demonstrate that this disentangled architecture achieves high-quality reconstruction in a single forward pass, followed by minimal fine-tuning.
  arXiv  Detail & Related papers  (2025-12-14T17:23:28Z)
• Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content [28.476493987089466]
  This paper presents M, a scalable Gaussian Splatting framework for efficient training in streaming tasks.<n>M achieves superior visual quality while significantly reducing training time compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-29T09:13:04Z)
• ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction [22.24139713363786]
  Existing 4D Gaussian Splatting methods rely on per-Gaussian deformation from a canonical space to target frames.<n>We propose Anchor-Driven Deformable and Compressed Gaussian Splatting (ADC-GS), a compact and efficient representation for dynamic scene reconstruction.<n>We show that ADC-GS outperforms the per-Gaussian deformation approaches in rendering speed by 300%-800%.
  arXiv  Detail & Related papers  (2025-05-13T03:13:40Z)
• Steepest Descent Density Control for Compact 3D Gaussian Splatting [72.54055499344052]
  3D Gaussian Splatting (3DGS) has emerged as a powerful real-time, high-resolution novel view.<n>We propose a theoretical framework that demystifies and improves density control in 3DGS.<n>We introduce SteepGS, incorporating steepest density control, a principled strategy that minimizes loss while maintaining a compact point cloud.
  arXiv  Detail & Related papers  (2025-05-08T18:41:38Z)
• Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling [50.34513854725803]
  Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors.<n>We propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-03-09T13:43:57Z)
• Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution [10.074968164380314]
  Implicit Neural Representations (INR) have been successfully employed for Arbitrary-scale Super-Resolution (ASR)<n>However, INR-based models need to query the multi-layer perceptron module numerous times and render a pixel in each query.<n>GS has shown its advantages over INR in both visual quality and rendering speed in 3D tasks, which motivates us to explore whether GS can be employed for the ASR task.
  arXiv  Detail & Related papers  (2025-01-12T15:14:58Z)
• Geometric Algebra Planes: Convex Implicit Neural Volumes [70.12234371845445]
  We show that GA-Planes is equivalent to a sparse low-rank factor plus low-resolution matrix. We also show that GA-Planes can be adapted for many existing representations.
  arXiv  Detail & Related papers  (2024-11-20T18:21:58Z)

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.