LinPrim: Linear Primitives for Differentiable Volumetric Rendering

• URL: http://arxiv.org/abs/2501.16312v4
• Date: Thu, 16 Oct 2025 17:58:17 GMT
• Title: LinPrim: Linear Primitives for Differentiable Volumetric Rendering
• Authors: Nicolas von Lützow, Matthias Nießner,
• Abstract summary: We introduce two new scene representations based on linear primitives.<n>We present a different octaiableizer that runs efficiently on GPU.<n>We demonstrate comparable performance to state-of-the-art methods.
• Score: 51.56484100374058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF or 3D Gaussians, we explore an alternative volumetric scene representation. More specifically, we introduce two new scene representations based on linear primitives - octahedra and tetrahedra - both of which define homogeneous volumes bounded by triangular faces. To optimize these primitives, we present a differentiable rasterizer that runs efficiently on GPUs, allowing end-to-end gradient-based optimization while maintaining real-time rendering capabilities. Through experiments on real-world datasets, we demonstrate comparable performance to state-of-the-art volumetric methods while requiring fewer primitives to achieve similar reconstruction fidelity. Our findings deepen the understanding of 3D representations by providing insights into the fidelity and performance characteristics of transparent polyhedra and suggest that adopting novel primitives can expand the available design space.

Related papers

• 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)
• Radiance Meshes for Volumetric Reconstruction [56.51690637804858]
  We introduce radiance meshes, a technique for representing radiance fields with constant density tetrahedral cells.<n>Our model is able to perform exact and fast volume rendering using both synthesisization and ray-tracing.<n>Our rendering method exactly evaluates the volume equation and enables high quality, real-time view on standard consumer hardware.
  arXiv  Detail & Related papers  (2025-12-03T18:57:03Z)
• FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction [18.570290675633732]
  We introduce Mesh-Guided 2D Gaussian Splatting, where 2D primitives are attached directly to template mesh faces with constrained position, rotation, and movement.<n>We leverage foundation models trained on large-scale datasets, such as Sapiens, to complement the limited visual cues from monocular videos.<n> Experimental evaluation demonstrates superior reconstruction quality compared to existing methods, with notable gains in geometric accuracy and appearance fidelity.
  arXiv  Detail & Related papers  (2025-09-18T08:41:41Z)
• 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)
• GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis [70.24111297192057]
  We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting.
  arXiv  Detail & Related papers  (2023-12-04T18:59:55Z)
• Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives [70.32817882783608]
  We present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. Unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points.
  arXiv  Detail & Related papers  (2023-07-11T17:58:31Z)
• NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support [43.5015470997138]
  We present a method for generating high-quality watertight manifold meshes from multi-view input images.<n>Our method combines the benefits of both worlds; we take the geometry obtained from neural fields, and further optimize the geometry as well as a compact neural texture representation.
  arXiv  Detail & Related papers  (2023-05-26T17:59:21Z)
• Learning to Render Novel Views from Wide-Baseline Stereo Pairs [26.528667940013598]
  We introduce a method for novel view synthesis given only a single wide-baseline stereo image pair. Existing approaches to novel view synthesis from sparse observations fail due to recovering incorrect 3D geometry. We propose an efficient, image-space epipolar line sampling scheme to assemble image features for a target ray.
  arXiv  Detail & Related papers  (2023-04-17T17:40:52Z)
• Generative Novel View Synthesis with 3D-Aware Diffusion Models [96.78397108732233]
  We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our method makes use of existing 2D diffusion backbones but, crucially, incorporates geometry priors in the form of a 3D feature volume. In addition to generating novel views, our method has the ability to autoregressively synthesize 3D-consistent sequences.
  arXiv  Detail & Related papers  (2023-04-05T17:15:47Z)
• Multi-View Mesh Reconstruction with Neural Deferred Shading [0.8514420632209809]
  State-of-the-art methods use both neural surface representations and neural shading. We represent surfaces as triangle meshes and build a differentiable rendering pipeline around triangle rendering and neural shading. We evaluate our runtime on a public 3D reconstruction dataset and show that it can match the reconstruction accuracy of traditional baselines while surpassing them in optimization.
  arXiv  Detail & Related papers  (2022-12-08T16:29:46Z)
• Extracting Triangular 3D Models, Materials, and Lighting From Images [59.33666140713829]
  We present an efficient method for joint optimization of materials and lighting from multi-view image observations. We leverage meshes with spatially-varying materials and environment that can be deployed in any traditional graphics engine.
  arXiv  Detail & Related papers  (2021-11-24T13:58:20Z)
• Point-Based Neural Rendering with Per-View Optimization [5.306819482496464]
  We introduce a general approach that is with MVS, but allows further optimization of scene properties in the space of input views. A key element of our approach is our new differentiable point-based pipeline. We use these elements together in our neural splatting, that outperforms all previous methods both in quality and speed in almost all scenes we tested.
  arXiv  Detail & Related papers  (2021-09-06T11:19:31Z)

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.