mlsanityData to 7 Oct 2026

Single-View 3D Reconstruction via SO(2)-Equivariant Gaussian Sculpting Networks

arXiv 2409.07245 ↗First posted 11 Sep 2024cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces SO(2)-Equivariant Gaussian Sculpting Networks (GSNs) as an approach for SO(2)-Equivariant 3D object reconstruction from single-view image observations. GSNs take a single observation as input to generate a Gaussian splat representation describing the observed object's geometry and texture. By using a shared feature extractor before decoding Gaussian colors, covariances, positions, and opacities, GSNs achieve extremely high throughput (>150FPS). Experiments demonstrate that GSNs can be trained efficiently using a multi-view rendering loss and are competitive, in quality, with expensive diffusion-based reconstruction algorithms. The GSN model is validated on multiple benchmark experiments. Moreover, we demonstrate the potential for GSNs to be used within a robotic manipulation pipeline for object-centric grasping.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 11 Sep 2024.

Builds on

25 of 37 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  6. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  7. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  8. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  9. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  10. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  11. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  12. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
13 more
  1. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  2. 2022Novel View Synthesis with Diffusion Modelscited by 299
  3. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  4. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  5. 2024A Survey on 3D Gaussian Splattingcited by 221
  6. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  7. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  8. 2021Vision-Only Robot Navigation in a Neural Radiance Worldcited by 153
  9. 20213D Neural Scene Representations for Visuomotor Controlcited by 110
  10. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  11. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  12. 2024GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Graspingcited by 77
  13. 2023How Many Views Are Needed to Reconstruct an Unknown Object Using NeRF?cited by 8

Built on by

Not cited yet.