Zero-shot Point Cloud Completion Via 2D Priors

• URL: http://arxiv.org/abs/2404.06814v1
• Date: Wed, 10 Apr 2024 08:02:17 GMT
• Title: Zero-shot Point Cloud Completion Via 2D Priors
• Authors: Tianxin Huang, Zhiwen Yan, Yuyang Zhao, Gim Hee Lee,
• Abstract summary: 3D point cloud completion is designed to recover complete shapes from partially observed point clouds. We propose a zero-shot framework aimed at completing partially observed point clouds across any unseen categories.
• Score: 52.72867922938023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D point cloud completion is designed to recover complete shapes from partially observed point clouds. Conventional completion methods typically depend on extensive point cloud data for training %, with their effectiveness often constrained to object categories similar to those seen during training. In contrast, we propose a zero-shot framework aimed at completing partially observed point clouds across any unseen categories. Leveraging point rendering via Gaussian Splatting, we develop techniques of Point Cloud Colorization and Zero-shot Fractal Completion that utilize 2D priors from pre-trained diffusion models to infer missing regions. Experimental results on both synthetic and real-world scanned point clouds demonstrate that our approach outperforms existing methods in completing a variety of objects without any requirement for specific training data.

Related papers

• 3D Point Cloud Generation via Autoregressive Up-sampling [60.05226063558296]
  We introduce a pioneering autoregressive generative model for 3D point cloud generation. Inspired by visual autoregressive modeling, we conceptualize point cloud generation as an autoregressive up-sampling process. PointARU progressively refines 3D point clouds from coarse to fine scales.
  arXiv  Detail & Related papers  (2025-03-11T16:30:45Z)
• Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning [61.14132533712537]
  We propose MAL-UPC, a framework that effectively leverages both region-level and category-specific geometric similarities to complete missing structures. Our MAL-UPC does not require any 3D complete supervision and only necessitates single-view partial observations in the training set.
  arXiv  Detail & Related papers  (2024-07-13T06:53:39Z)
• Zero-Shot Point Cloud Registration [94.39796531154303]
  ZeroReg is the first zero-shot point cloud registration approach that eliminates the need for training on point cloud datasets. The cornerstone of ZeroReg is the novel transfer of image features from keypoints to the point cloud, enriched by aggregating information from 3D geometric neighborhoods. On benchmarks such as 3DMatch, 3DLoMatch, and ScanNet, ZeroReg achieves impressive Recall Ratios (RR) of over 84%, 46%, and 75%, respectively.
  arXiv  Detail & Related papers  (2023-12-05T11:33:16Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds [44.02541315496045]
  Point cloud completion aims to recover the complete shape based on a partial observation. Existing methods require either complete point clouds or multiple partial observations of the same object for learning. We present Partial2Complete, the first self-supervised framework that completes point cloud objects.
  arXiv  Detail & Related papers  (2023-07-27T09:31:01Z)
• Variational Relational Point Completion Network for Robust 3D Classification [59.80993960827833]
  Vari point cloud completion methods tend to generate global shape skeletons hence lack fine local details. This paper proposes a variational framework, point Completion Network (VRCNet) with two appealing properties. VRCNet shows great generalizability and robustness on real-world point cloud scans.
  arXiv  Detail & Related papers  (2023-04-18T17:03:20Z)
• Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion [53.93172686610741]
  Cross-PCC is an unsupervised point cloud completion method without requiring any 3D complete point clouds. To take advantage of the complementary information from 2D images, we use a single-view RGB image to extract 2D features. Our method even achieves comparable performance to some supervised methods.
  arXiv  Detail & Related papers  (2022-12-01T15:11:21Z)
• PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples [63.84378007819262]
  We propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones. We show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01.
  arXiv  Detail & Related papers  (2022-11-22T14:15:41Z)
• Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds [14.056949618464394]
  Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. We propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds. We introduce Point-Syn2Real, a new benchmark dataset for cross-domain learning on point clouds.
  arXiv  Detail & Related papers  (2022-10-31T01:53:51Z)
• Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion [10.649666758735663]
  Real-world sensors often produce incomplete, irregular, and noisy point clouds. This paper proposes RaPD, a novel semi-supervised point cloud completion method.
  arXiv  Detail & Related papers  (2022-04-20T02:14:20Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering [21.563862632172363]
  We propose a self-supervised point cloud upsampling network (SSPU-Net) to generate dense point clouds without using ground truth. To achieve this, we exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images.
  arXiv  Detail & Related papers  (2021-08-01T13:26:01Z)
• Point Set Voting for Partial Point Cloud Analysis [26.31029112502835]
  techniques for point cloud classification and segmentation have in recent years achieved incredible performance driven in part by leveraging large synthetic datasets. This paper proposes a general model for partial point clouds analysis wherein the latent feature encoding a complete point clouds is inferred by applying a local point set voting strategy.
  arXiv  Detail & Related papers  (2020-07-09T03:37:31Z)

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.