DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

• URL: http://arxiv.org/abs/2606.12189v1
• Date: Wed, 10 Jun 2026 15:13:14 GMT
• Title: DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
• Abstract summary: DynaTok is a point-based framework for correspondence-free 4D reconstruction from partial point sequences without images.<n>A flow-matching decoder then reconstructs complete, temporally consistent 4D point-temporal observations.
• Score: 86.5916611076068
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address 4D reconstruction from partial point cloud sequences, where depth-sensor observations are incomplete, unordered, and lack explicit temporal correspondences. This geometry-only setting is challenging due to missing observations and ambiguous dynamics. While recent progress has largely relied on image-based methods, existing point-based approaches typically focus on single objects, assume relatively complete inputs, or require explicit correspondences. To address these limitations, we propose DynaTok, a point-based framework for correspondence-free 4D reconstruction from partial point cloud sequences without images. DynaTok encodes frames into compact latent tokens, aggregates incomplete observations over time with a Transformer-based spatiotemporal encoder, and decouples geometry and motion through residual tokens in a unified model. A flow-matching decoder then reconstructs complete, temporally consistent 4D point-cloud sequences conditioned on the latent tokens. Experiments on object- and scene-level benchmarks demonstrate improved reconstruction quality and temporal coherence from partial point cloud observations. Project page: https://wrchen530.github.io/dynatok/.

Related papers

• Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videos [8.592776018057192]
  We propose a JEPA-style framework that learns from unsupervised point clouds through latent point-temporal prediction.<n>We show that the learned representations improve downstream fine-level annotations, limited-level annotations, and cross-dataset transfer.<n>These results suggest that JEPA-style prediction is a promising alternative to reconstruction-centered pretraining for 4D point cloud videos.
  arXiv  Detail & Related papers  (2026-08-25T05:38:43Z)
• Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction [56.32589034046427]
  We introduce Dynamic Point Maps (DPM), extending standard point maps to support 4D tasks such as motion segmentation, scene flow estimation, 3D object tracking, and 2D correspondence.<n>We train a DPM predictor on a mixture of synthetic and real data and evaluate it across diverse benchmarks for video depth prediction, dynamic point cloud reconstruction, 3D scene flow and object pose tracking, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-20T16:41:50Z)
• 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)
• GPN: Generative Point-based NeRF [0.65268245109828]
  We propose using Generative Point-based NeRF (GPN) to reconstruct and repair a partial cloud. The repaired point cloud can achieve multi-view consistency with the captured images at high spatial resolution.
  arXiv  Detail & Related papers  (2024-04-12T08:14:17Z)
• Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking [52.393359791978035]
  Motion2VecSets is a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. We parameterize 4D dynamics with latent sets instead of using global latent codes. For more temporally-coherent object tracking, we synchronously denoise deformation latent sets and exchange information across multiple frames.
  arXiv  Detail & Related papers  (2024-01-12T15:05:08Z)
• ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models [77.84408427496025]
  State-of-the-art 3D point cloud registration methods rely on labeled 3D datasets for training.<n>We introduce ZeroReg, a zero-shot registration approach that utilizes 2D foundation models to predict 3D correspondences.
  arXiv  Detail & Related papers  (2023-12-05T11:33:16Z)
• Point Scene Understanding via Disentangled Instance Mesh Reconstruction [21.92736190195887]
  We propose aDisentangled Instance Mesh Reconstruction (DIMR) framework for effective point scene understanding. A segmentation-based backbone is applied to reduce false positive object proposals. We leverage a mesh-aware latent code space to disentangle the processes of shape completion and mesh generation.
  arXiv  Detail & Related papers  (2022-03-31T06:36:07Z)
• RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction [19.535169371240073]
  We introduce RfD-Net that jointly detects and reconstructs dense object surfaces directly from point clouds. We decouple the instance reconstruction into global object localization and local shape prediction. Our approach consistently outperforms the state-of-the-arts and improves over 11 of mesh IoU in object reconstruction.
  arXiv  Detail & Related papers  (2020-11-30T12:58:05Z)
• CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations [72.4716073597902]
  We propose a method to learn object Canonical Point Cloud Representations of dynamically or moving objects. We demonstrate the effectiveness of our method on several applications including shape reconstruction, camera pose estimation, continuoustemporal sequence reconstruction, and correspondence estimation.
  arXiv  Detail & Related papers  (2020-08-06T17:58:48Z)

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.