MLP Splatting: Object-Centric Neural Fields

• URL: http://arxiv.org/abs/2606.03877v1
• Date: Tue, 02 Jun 2026 16:46:16 GMT
• Title: MLP Splatting: Object-Centric Neural Fields
• Abstract summary: 3D representations are fundamental to scene rendering, understanding, and interaction.<n>Recent approaches, such as 3D Gaussian Splatting and Neural Radiance Fields, achieve impressive photorealistic novel-view synthesis.<n>We present scene-Splatting, a method that enables scene decomposition via a few expressive light-field primitives.
• Score: 24.860735567401687
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 3D representations are fundamental to scene rendering, understanding, and interaction. Recent approaches, such as 3D Gaussian Splatting and Neural Radiance Fields, achieve impressive photorealistic novel-view synthesis, but lack the ability to easily decompose scene elements into a few primitives, requiring additional segmentation or grouping for object-level manipulation. We present MLP-Splatting, a method that enables scene decomposition via a few expressive light-field primitives while providing photorealistic novel-view synthesis. MLP-Splatting models each primitive as an independent compact MLP with localized spatial support that predicts radiance and opacity. In contrast to low-level Gaussian primitives or a single global radiance field, our neural primitives provide greater expressive capacity while remaining spatially localized. Rendering is performed through efficient sparse volumetric compositing over ray-primitive interactions. Our primitives are supervised using RGB supervision alone, which yields primitives that represent local scene regions often corresponding to objects or object parts, enabling interactive object-level editing without segmentation masks by selecting a handful of primitives. Our method, augmented with optional semantic feature distillation, enables open-vocabulary scene interaction and open-set instant segmentation. Compared to state-of-the-art methods, we achieve substantially lower memory usage (1/15$\times$) and faster rendering (3$\times$), as we show in our experiments compared to semantic 3DGS methods. Project Page: https://shinjeongkim.com/mlp-splatting

Related papers

• Floating Radiance Networks [9.113967709616503]
  FlaRe is a neural scene representation combining explicit ray-traceable geometry with continuous neural radiance functions.<n>A lightweight decoder shared across the scene maps this descriptor, local surface coordinates, and viewing direction to color and opacity.
  arXiv  Detail & Related papers  (2026-08-06T11:50:01Z)
• NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting [0.6516563485069087]
  3D Gaussianting can exploit frustum culling and level-of-detail strategies to accelerate rendering of scenes containing a large number of primitives.<n>We propose a method to learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared across instances of an asset in a scene.<n>By querying it for Gaussians within the viewing frustum prior to rendering, our method can discard occluded primitives during rendering.
  arXiv  Detail & Related papers  (2025-11-24T15:11:12Z)
• Splat the Net: Radiance Fields with Splattable Neural Primitives [64.84677516748998]
  splattable neural primitives reconcile expressivity of neural models with the efficiency of primitive-based splatting.<n>Our representation supports integration along view rays without the need for costly ray marching.
  arXiv  Detail & Related papers  (2025-10-09T17:31:11Z)
• OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting [52.40697058096931]
  3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction.<n>We introduce an approach for open-vocabulary 3D instance segmentation without requiring manual labeling, termed OpenSplat3D.<n>We show results on LERF-mask and LERF-OVS as well as the full ScanNet++ validation set, demonstrating the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-06-09T12:37:15Z)
• LinPrim: Linear Primitives for Differentiable Volumetric Rendering [51.56484100374058]
  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.
  arXiv  Detail & Related papers  (2025-01-27T18:49:38Z)
• DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering [18.72451738333928]
  DeSplat is a novel method for separating distractors and static scene elements purely based on volume rendering of Gaussian primitives.<n>We demonstrate DeSplat's effectiveness on three benchmark data sets for distractor-free novel view synthesis.
  arXiv  Detail & Related papers  (2024-11-29T15:00:38Z)
• Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes [59.17785932398617]
  High-quality view synthesis relies on volume rendering, splatting, or surface rendering.<n>We present a novel representation for real-time view synthesis where the number of sampling locations is small and bounded.<n>We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order.
  arXiv  Detail & Related papers  (2024-09-04T07:18:26Z)
• GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis [1.6574413179773757]
  GenLayNeRF is a generalizable layered scene representation for free-viewpoint rendering of multiple human subjects. We divide the scene into multi-human layers anchored by the 3D body meshes. We extract point-wise image-aligned and human-anchored features which are correlated and fused.
  arXiv  Detail & Related papers  (2023-09-20T20:37:31Z)
• 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)
• PaletteNeRF: Palette-based Appearance Editing of Neural Radiance Fields [60.66412075837952]
  We present PaletteNeRF, a novel method for appearance editing of neural radiance fields (NeRF) based on 3D color decomposition. Our method decomposes the appearance of each 3D point into a linear combination of palette-based bases. We extend our framework with compressed semantic features for semantic-aware appearance editing.
  arXiv  Detail & Related papers  (2022-12-21T00:20:01Z)
• Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation [28.387277178967516]
  We present Panoptic Neural Fields (PNF), an object-aware neural scene representation. PNF decomposes a scene into a set of objects (things) and background (stuff) We find that our model can be used effectively for several tasks like novel view, 2D panoptic segmentation, 3D scene editing, and multiview depth prediction.
  arXiv  Detail & Related papers  (2022-05-09T14:34:55Z)

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.