Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots

• URL: http://arxiv.org/abs/2608.26383v1
• Date: Wed, 26 Aug 2026 20:16:02 GMT
• Title: Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots
• Abstract summary: 3D reconstruction pipelines can turn raw camera streams into actionable object representations within the latency budget of a physical control loop.<n>We present a compute-platform benchmark of neural 3D reconstruction methods, evaluating NeRF and 3D Gaussian Splatting training and rendering on GPU-enabled computing devices.<n>Our results show that Gaussian Splatting yields higher rendering quality than NeRF at greater GPU cost, and that onboard compute is insufficient for full per-scene optimization at interactive rates.
• Score: 2.957742819151154
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous robots performing laboratory tasks depend on 3D reconstruction pipelines that can turn raw camera streams into actionable object representations within the latency budget of a physical control loop. Neural 3D reconstruction methods have demonstrated high-quality view synthesis, but their real-time viability across the compute platforms on which laboratory robots actually run remains poorly characterized. In this work, we present a systematic compute-platform benchmark of neural 3D reconstruction methods, evaluating NeRF and 3D Gaussian Splatting training and rendering on GPU-enabled computing devices ranging from single-board computers to server-class nodes, and place Meta's SAM3D single-image reconstruction on the same axes to quantify its latency and fidelity gap relative to per-scene optimization. Our results show that Gaussian Splatting yields higher rendering quality than NeRF at greater GPU cost, and that onboard compute is insufficient for full per-scene optimization at interactive rates. Our preliminary assessment on SAM3D indicates that it delivers plausible object geometry within seconds, but with detail mismatches that can compromise downstream manipulation. Together, these findings motivate tiered pipelines in which lightweight feed-forward reconstruction sustains the real-time perception-and-tracking loop for laboratory robots, while heavier neural reconstruction is scheduled selectively on suitable compute.

Related papers

• RORA: Realistic Object Reconstruction with Articulation [10.305820103142269]
  We propose the first end-to-end pipeline that reconstructs simulation-ready assets with accurate articulation from a single static object video input.<n>Our approach exports a hybrid representation combining 3DGS for rendering and mesh-based geometry for physical interaction.<n>We have shown that our method achieves precise articulation results on partnet-mobility-v0 dataset and real objects.
  arXiv  Detail & Related papers  (2026-08-05T13:36:58Z)
• Stipple: Real-Time Incremental Gaussian Splatting with Visual-Inertial Tracking [45.88028371034407]
  We propose a new method that tracks and reconstructs simultaneously in real-time by leveraging an efficient visual-inertial tracking system.<n>We show that many of the heavy preprocessing and training steps of 3DGS can be replaced with a more efficient incremental training strategy.
  arXiv  Detail & Related papers  (2026-08-02T02:17:05Z)
• Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction [50.5449251266956]
  This paper addresses the task of large-scale 3D scene reconstruction from long video sequences.<n>Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D priors or geometric constraints.<n>We propose a novel neural global context representation that efficiently compresses and retains long-range scene information.
  arXiv  Detail & Related papers  (2026-04-09T17:59:50Z)
• Robo3R: Enhancing Robotic Manipulation with Accurate Feed-Forward 3D Reconstruction [70.06600045165905]
  3D spatial perception is fundamental to general robotic manipulation, yet obtaining reliable, high-quality 3D geometry remains challenging.<n>We introduce Robo3R, a manipulation-ready 3D reconstruction model that predicts accurate, metric-scale scene geometry directly from RGB images and robot states in real time.<n>We observe consistent gains in performance, suggesting the promise of this alternative 3D sensing module for robotic manipulation.
  arXiv  Detail & Related papers  (2026-02-10T18:58:15Z)
• Particulate: Feed-Forward 3D Object Articulation [89.78788418174946]
  Particulate is a feed-forward approach that, given a single static 3D mesh of an everyday object, directly infers all attributes of the underlying articulated structure.<n>We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets.<n>During inference, Particulate lifts the network's feed-forward prediction to the input mesh, yielding a fully articulated 3D model in seconds.
  arXiv  Detail & Related papers  (2025-12-12T18:59:51Z)
• Integrated Pipeline for Monocular 3D Reconstruction and Finite Element Simulation in Industrial Applications [1.3908352231737158]
  This paper proposes an integrated workflow, which integrates high-fidelity 3D reconstruction based on monocular video, finite element simulation analysis, and mixed reality visual display.<n>Experiments show that the method has good simulation efficiency and visualization effect while maintaining high geometric accuracy.
  arXiv  Detail & Related papers  (2025-06-16T14:57:05Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion [54.197343533492486]
  Event3DGS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion. Experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks. Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.
  arXiv  Detail & Related papers  (2024-06-05T06:06:03Z)
• Sparse 3D Reconstruction via Object-Centric Ray Sampling [20.874406440346462]
  We propose a novel method for 3D object reconstruction from a sparse set of views captured from a 360-degree camera rig. We represent the object through a hybrid model that uses both an calibrated-based neural representation and a triangle mesh. We work with sparse views on the Google's Scanned Objects, Tank and Temples and MVMC Car datasets.
  arXiv  Detail & Related papers  (2023-09-06T13:54:31Z)
• NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions [97.27105725738016]
  integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs) has transformed 3D-aware generation from single-view images. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations.
  arXiv  Detail & Related papers  (2023-03-22T18:59:48Z)
• OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction [14.130915525776055]
  RGBD-based real-time dynamic 3D reconstruction suffers from inaccurate inter-frame motion estimation. We propose OcclusionFusion, a novel method to calculate occlusion-aware 3D motion to guide the reconstruction. Our technique outperforms existing single-view-based real-time methods by a large margin.
  arXiv  Detail & Related papers  (2022-03-15T15:09:01Z)
• Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity [3.359622001455893]
  Learning-based 3D object reconstruction enables single- or few-shot estimation of 3D object models. Existing 3D reconstruction techniques optimize for visual reconstruction fidelity, typically measured by chamfer distance or voxel IOU. We propose ARM, an amodal 3D reconstruction system that introduces a stability prior over object shapes, (2) a connectivity prior, and (3) a multi-channel input representation.
  arXiv  Detail & Related papers  (2020-09-28T08:52:54Z)

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.