paper-with-me

Papers

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

2026-06-10 · Weirong Chen, Keisuke Tateno, Hidenobu Matsuki, Michael Niemeyer, Daniel Cremers, Federico Tombari arxiv

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/.

📄 PDF Abstract BibTeX arXiv:2606.12189

Code (0)

등록된 구현이 없습니다.

Tasks

Point Clouds

Similar Papers 제목 키워드 기반

DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs

2026-05-19 · Minyoung Park, Taehun Kong, Sangjun Ahn arxiv

Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visual tokens extracted from long video sequences incurs prohibitive com…

Multimodal Reasoning

Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement

2022-01-09 · Meng-Shiun Tsai, Pei-Ze Chiang, Yi-Hsuan Tsai, Wei-Chen Chiu

Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised fra…

DisentanglementRepresentation LearningSelf-Supervised Learning

Variational Relational Point Completion Network for Robust 3D Classification

2023-04-18 · Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang 외

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons a…

3D ClassificationClassificationPoint Cloud Completion

Variational Relational Point Completion Network

2021-04-20 · CVPR 2021 1 · Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang 외

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they …

Point Cloud Completion

Inferring Point Clouds from Single Monocular Images by Depth Intermediation

2018-12-04 · Wei Zeng, Sezer Karaoglu, Theo Gevers

In this paper, we propose a pipeline to generate 3D point cloud of an object from a single-view RGB image. Most previous work predict the 3D point coordinates from single RGB images directly. We decompose this problem in…

3D Object ReconstructionDepth EstimationObjectObject Reconstruction+1