Recent Advances and Trends in Learning-based 3D Representations

• URL: http://arxiv.org/abs/2606.04871v1
• Date: Wed, 03 Jun 2026 13:35:50 GMT
• Title: Recent Advances and Trends in Learning-based 3D Representations
• Abstract summary: The selection of an appropriate 3D representation dictates the efficiency, quality, and capabilities of modern computer vision and graphics pipelines for tasks such as 3D reconstruction, novel-view synthesis and rendering, shape and motion analysis, recognition, and generation.<n>Recent neural and primitive-based representations offer compact and differentiable alternatives opening a wide range of opportunities in applications such as games, AR/VR, autonomous driving, robot navigation, and medical imaging.<n>For each type of representation, we present the general formulation and its variants, discuss its benefits and limitations, and highlight key applications.
• Score: 6.265283624249999
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The selection of an appropriate 3D representation is a fundamental design decision that dictates the efficiency, quality, and capabilities of modern computer vision and graphics pipelines for tasks such as 3D reconstruction, novel-view synthesis and rendering, shape and motion analysis, recognition, and generation. While traditional representations (\eg meshes, point clouds, and volumetric grids) remain standard outputs of 3D sensors (\eg LiDAR and 3D scanners) and are widely used in downstream applications (\eg editing and simulation), recent neural and primitive-based representations (\eg 3D Gaussian Splatting) offer compact and differentiable alternatives opening a wide range of opportunities in applications such as games, AR/VR, autonomous driving, robot navigation, and medical imaging, to name a few. The goal of this paper is to survey the main families of 3D representations from discrete explicit formats to continuous implicit fields based either on neural rendering or primitive splatting. For each type of representation, we present the general formulation and its variants, discuss its benefits and limitations, and highlight key applications. We conclude the paper by outlining the open challenges and potential directions for future research. Distinct from recent surveys that broadly cover 3D object and scene reconstruction, this paper provides a focused analysis on the evolution of 3D representations themselves. We specifically emphasize the paradigm shift toward implicit representations, offering a novel perspective on how these emerging formats fundamentally alter 3D/4D workflows.

Related papers

• Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective [91.23306722968509]
  Generalizable feed-forward 3D reconstruction has witnessed rapid development in recent years.<n>Existing feed-forward approaches share similar high-level architectural patterns.<n>We propose a novel taxonomy centered on model design strategies that are agnostic to the output format.
  arXiv  Detail & Related papers  (2026-04-15T16:07:18Z)
• What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models [68.35971238810863]
  Current SLAM and localization systems rely on sparse representations like point clouds and voxels.<n>NeRF, 3DGS, and foundation models are well-suited for integrating high-level semantic features and language-based priors.
  arXiv  Detail & Related papers  (2025-12-03T03:57:01Z)
• Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey [171.72616707259306]
  3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins.<n>Recent advances in feed-forward approaches, driven by deep learning, have revolutionized this field by enabling fast and generalizable 3D reconstruction and view synthesis.
  arXiv  Detail & Related papers  (2025-07-19T06:13:25Z)
• End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards [8.953379216683732]
  We propose an end-to-end differentiable, reinforcement-learning-free framework that embeds human feedback, expressed as differentiable reward functions, directly into the 3D texture pipeline.<n>By back-propagating preference signals through both geometric and appearance modules, our method generates textures that respect the 3D geometry structure and align with desired criteria.
  arXiv  Detail & Related papers  (2025-06-23T06:24:12Z)
• 3D Representation Methods: A Survey [0.0]
  3D representation has experienced significant advancements, driven by the increasing demand for high-fidelity 3D models in various applications. This review examines the development and current state of 3D representation methods, highlighting their research trajectories, innovations, strength and weakness.
  arXiv  Detail & Related papers  (2024-10-09T02:01:05Z)
• Diffusion Models in 3D Vision: A Survey [18.805222552728225]
  3D vision has become a crucial field within computer vision, powering a range of applications such as autonomous driving, robotics, augmented reality, and medical imaging.<n>We review the state-of-the-art methods that use diffusion models for 3D visual tasks, including but not limited to 3D object generation, shape completion, point-cloud reconstruction, and scene construction.<n>We discuss potential solutions, including improving computational efficiency, enhancing multimodal fusion, and exploring the use of large-scale pretraining for better generalization across 3D tasks.
  arXiv  Detail & Related papers  (2024-10-07T04:12:23Z)
• A Survey on 3D Gaussian Splatting [61.50539646390613]
  3D Gaussian splatting (GS) has emerged as a transformative technique in radiance fields.<n>We provide the first systematic overview of the recent developments and critical contributions in 3D GS.<n>By enabling unprecedented rendering speed, 3D GS opens up a plethora of applications, ranging from virtual reality to interactive media and beyond.
  arXiv  Detail & Related papers  (2024-01-08T13:42:59Z)
• Deep Generative Models on 3D Representations: A Survey [81.73385191402419]
  Generative models aim to learn the distribution of observed data by generating new instances. Recently, researchers started to shift focus from 2D to 3D space. representing 3D data poses significantly greater challenges.
  arXiv  Detail & Related papers  (2022-10-27T17:59:50Z)
• Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields [82.21033337949757]
  This paper introduces a ray-based volumetric uncertainty estimator, which computes the entropy of the weight distribution of the color samples along each ray of the object's implicit neural representation. We show that it is possible to infer the uncertainty of the underlying 3D geometry given a novel view with the proposed estimator. We present a next-best-view selection policy guided by the ray-based volumetric uncertainty in neural radiance fields-based representations.
  arXiv  Detail & Related papers  (2022-09-17T21:28:57Z)

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.