Learning View-Dependent Splatting Kernels

• URL: http://arxiv.org/abs/2605.25426v1
• Date: Mon, 25 May 2026 04:57:25 GMT
• Title: Learning View-Dependent Splatting Kernels
• Abstract summary: We learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency.<n>We extend the idea to learn general 2D kernels for 2D splatting as well as image representation.
• Score: 19.881166133057764
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. Our volumetric primitive is defined as a bounding ellipsoid and a 3D-kernel latent vector. We first learn a projection network to output a 2D-kernel latent, taking the attributes of the ellipsoid and the 3D-kernel latent as input. Next, the result is sent to a decoder to produce a radially symmetric 2D kernel in terms of Mahalanobis distance, bounded by the projected ellipsoid. The neural networks along with per-primitive attributes are jointly optimized. The effectiveness of our approach is demonstrated on standard benchmarks, comparing favorably against state-of-the-art techniques on both analytical and learned kernels. Finally, we extend the idea to learn general 2D kernels for 2D splatting as well as image representation.

Related papers

• FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation [48.928051741750124]
  We propose a scalable image-to-3DGS framework that boosts representation learning and cross-modal alignment during generation.<n>FLUX3D yields substantial improvements in appearance fidelity and significantly outperforms all state-of-the-art (SOTA) methods in generating high-quality 3DGS assets.
  arXiv  Detail & Related papers  (2026-06-23T17:52:21Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• Feature Visualization in 3D Convolutional Neural Networks [1.3154296174423619]
  We propose a novel visualization approach for 3D convolutional kernels that disentangles their texture and motion preferences.<n>Applying our approach to visualize kernels at various depths of several pre-trained models, we find that the resulting visualizations--particularly those capturing motion--clearly reveal the preferred dynamic patterns encoded by 3D kernels.
  arXiv  Detail & Related papers  (2025-05-12T09:31:31Z)
• 3DGS$^2$: Near Second-order Converging 3D Gaussian Splatting [26.94968605302451]
  3D Gaussian Splatting (3DGS) has emerged as a mainstream solution for novel view synthesis and 3D reconstruction.<n>This paper introduces a (near) second-order convergent training algorithm for 3DGS, leveraging its unique properties.
  arXiv  Detail & Related papers  (2025-01-22T22:28:11Z)
• GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views [67.34073368933814]
  We propose a generalizable Gaussian Splatting approach for high-resolution image rendering under a sparse-view camera setting. We train our Gaussian parameter regression module on human-only data or human-scene data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. Experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.
  arXiv  Detail & Related papers  (2024-11-18T08:18:44Z)
• DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions [41.55908366474901]
  We introduce a novel approach that harnesses both 2D and 3D attentions to enable highly accurate depth completion. We evaluate our method, DeCoTR, on established depth completion benchmarks.
  arXiv  Detail & Related papers  (2024-03-18T19:22:55Z)
• NEAT: Distilling 3D Wireframes from Neural Attraction Fields [52.90572335390092]
  This paper studies the problem of structured lineframe junctions using 3D reconstruction segments andFocusing junctions. ProjectNEAT enjoys the joint neural fields and view without crossart matching from scratch.
  arXiv  Detail & Related papers  (2023-07-14T07:25:47Z)
• Unleash the Potential of Image Branch for Cross-modal 3D Object Detection [67.94357336206136]
  We present a new cross-modal 3D object detector, namely UPIDet, which aims to unleash the potential of the image branch from two aspects. First, UPIDet introduces a new 2D auxiliary task called normalized local coordinate map estimation. Second, we discover that the representational capability of the point cloud backbone can be enhanced through the gradients backpropagated from the training objectives of the image branch.
  arXiv  Detail & Related papers  (2023-01-22T08:26:58Z)
• Improving neural implicit surfaces geometry with patch warping [12.106051690920266]
  We argue that this comes from the difficulty to learn and render high frequency textures with neural networks. We propose to add to the standard neural rendering optimization a direct photo-consistency term across the different views. We evaluate our approach, dubbed NeuralWarp, on the standard DTU and EPFL benchmarks and show it outperforms state of the art unsupervised implicit surfaces reconstructions by over 20% on both datasets.
  arXiv  Detail & Related papers  (2021-12-17T17:43:50Z)
• Learning Joint 2D-3D Representations for Depth Completion [90.62843376586216]
  We design a simple yet effective neural network block that learns to extract joint 2D and 3D features. Specifically, the block consists of two domain-specific sub-networks that apply 2D convolution on image pixels and continuous convolution on 3D points.
  arXiv  Detail & Related papers  (2020-12-22T22:58:29Z)

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.