DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models

• URL: http://arxiv.org/abs/2605.26949v1
• Date: Tue, 26 May 2026 12:40:52 GMT
• Title: DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models
• Abstract summary: We present DinoComplete, a framework that augments geometric reconstruction with semantic priors distilled from DINO features.<n>Experiments on unseen ShapeNet categories and ScanNet objects show that DinoComplete achieves stronger completion quality than prior deterministic and generative based completion methods.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a deterministic and efficient shape completion framework that augments geometric reconstruction with voxel-aligned semantic priors distilled from DINO features. First, we construct multi-view DINO feature volumes aligned with ShapeNet data and train a student network to predict dense semantic features directly from incomplete shapes. These predicted features capture global structure and part-aware semantic context while remaining aligned with the underlying geometry. We then integrate these distilled features into a completion network, where geometric and semantic voxel representations are fused through voxel state-space modeling. To enable efficient long-range reasoning without sacrificing resolution, we introduce a multi-scale voxel Mamba module that refines the fused features by combining full-grid and chunk-wise sequence modeling. Experiments on unseen ShapeNet categories and ScanNet objects show that DinoComplete achieves stronger completion quality than prior deterministic and generative based completion methods while using fewer parameters, requiring lower memory, and achieving faster inference. Our results demonstrate that distilling semantic priors from visual foundation models improves generalization and robustness in 3D shape completion.

Related papers

• Pano3D: Unified 3D Reconstruction and Panoptic Segmentation [68.18993232814061]
  We introduce an approach that performs 3D reconstruction and 3D panoptic segmentation in a unified framework.<n>We build on existing 3D reconstruction models and augment them with a set-based mask decoder.<n>Our method achieves state-of-the-art performance in 3D panoptic segmentation across ScanNet, ScanNet200, and ScanNet++ datasets.
  arXiv  Detail & Related papers  (2026-06-12T09:43:13Z)
• VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching [39.72379398607968]
  We introduce VolFill, a generative framework that predicts the 3D structure of the complete scene.<n>Our method utilizes a hybrid 3D VAE to compress sparse truncated unsigned distance function grids into a compact latent space.
  arXiv  Detail & Related papers  (2026-05-29T15:59:20Z)
• Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective [8.276620253870338]
  Point cloud completion aims to reconstruct complete 3D shapes from partial observations.<n>Most methods still follow a Completion-by-Inpainting paradigm.<n>We propose Completion-by-Correction, which begins with a complete shape prior and performs feature-space correction to align it with the partial observation.
  arXiv  Detail & Related papers  (2025-11-15T11:51:13Z)
• ArchComplete: Autoregressive 3D Architectural Design Generation with Hierarchical Diffusion-Based Upsampling [0.0]
  ArchComplete is a two-stage voxel-based 3D generative pipeline consisting of a vector-quantised model.<n>Key to our pipeline is (i) learning a contextually rich codebook of local patch embeddings, optimised alongside a 2.5D perceptual loss.<n> ArchComplete autoregressively generates models at the resolution of $643$ and progressively refines them up to $5123$, with voxel sizes as small as $ approx 9textcm$.
  arXiv  Detail & Related papers  (2024-12-23T20:13:27Z)
• 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.<n>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)
• Robust 3D Tracking with Quality-Aware Shape Completion [67.9748164949519]
  We propose a synthetic target representation composed of dense and complete point clouds depicting the target shape precisely by shape completion for robust 3D tracking. Specifically, we design a voxelized 3D tracking framework with shape completion, in which we propose a quality-aware shape completion mechanism to alleviate the adverse effect of noisy historical predictions.
  arXiv  Detail & Related papers  (2023-12-17T04:50:24Z)
• DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image [31.154786931081087]
  We propose a novel bi-channel Transformer architecture, integrated with parameterized deformable models, to simultaneously estimate the global and local deformations of primitives. DeFormer achieves better reconstruction accuracy over the state-of-the-art, and visualizes with consistent semantic correspondences for improved interpretability.
  arXiv  Detail & Related papers  (2023-09-22T02:46:43Z)
• DiffComplete: Diffusion-based Generative 3D Shape Completion [114.43353365917015]
  We introduce a new diffusion-based approach for shape completion on 3D range scans. We strike a balance between realism, multi-modality, and high fidelity. DiffComplete sets a new SOTA performance on two large-scale 3D shape completion benchmarks.
  arXiv  Detail & Related papers  (2023-06-28T16:07:36Z)
• 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)
• MFM-Net: Unpaired Shape Completion Network with Multi-stage Feature Matching [38.63975659511946]
  We propose a novel unpaired shape completion network, named MFM-Net, which decomposes the learning of geometric correspondence into multi-stages. MFM-Net makes use of a more comprehensive understanding to establish the geometric correspondence between complete and incomplete shapes.
  arXiv  Detail & Related papers  (2021-11-23T16:10:06Z)
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [86.77318031029404]
  We propose a framework that performs scene reconstruction and semantic scene completion jointly in an incremental and real-time manner. Our framework relies on a novel neural architecture designed to process occupancy maps and leverages voxel states to accurately and efficiently fuse semantic completion with the 3D global model.
  arXiv  Detail & Related papers  (2020-10-26T15:31:52Z)
• Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion [53.885984328273686]
  Implicit Feature Networks (IF-Nets) deliver continuous outputs, can handle multiple topologies, and complete shapes for missing or sparse input data. IF-Nets clearly outperform prior work in 3D object reconstruction in ShapeNet, and obtain significantly more accurate 3D human reconstructions.
  arXiv  Detail & Related papers  (2020-03-03T11:14:29Z)

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.