DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction

Yuxin Yao; Siyu Ren; Junhui Hou; Zhi Deng; Juyong Zhang; Wenping Wang

doi:10.1007/978-3-031-73414-4_16

DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction

Yuxin Yao, Siyu Ren, Junhui Hou^*, Zhi Deng, Juyong Zhang, Wenping Wang

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf. © 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG 2025

Original language	English
Title of host publication	Computer Vision – ECCV 2024
Subtitle of host publication	18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXXIII
Editors	Aleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, Gül Varol
Publisher	Springer, Cham
Pages	271-288
ISBN (Electronic)	978-3-031-73414-4
ISBN (Print)	978-3-031-73413-7
DOIs	https://doi.org/10.1007/978-3-031-73414-4_16
Publication status	Published - 25 Oct 2024
Event	18th European Conference on Computer Vision (ECCV 2024) - MiCo Milano, Milan, Italy Duration: 29 Sept 2024 → 4 Oct 2024 https://eccv.ecva.net/

Publication series

Name	Lecture Notes in Computer Science
Volume	15091

Conference

Conference	18th European Conference on Computer Vision (ECCV 2024)
Abbreviated title	ECCV2024
Place	Italy
City	Milan
Period	29/09/24 → 4/10/24
Internet address	https://eccv.ecva.net/

Bibliographical note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Funding

This project was supported by the Hong Kong Research Grants Council under Grants 11219324, 11219422, and 11202320.

Research Keywords

Dynamic Surface Reconstruction
Temporally Consistent Meshes
Low-Dimensional Deformation
Point Cloud Sequences

RGC Funding Information

RGC-funded

Access Output

10.1007/978-3-031-73414-4_16

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Yao, Y., Ren, S., Hou, J., Deng, Z., Zhang, J., & Wang, W. (2024). DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.), Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXXIII (pp. 271-288). (Lecture Notes in Computer Science; Vol. 15091). Springer, Cham. https://doi.org/10.1007/978-3-031-73414-4_16

Yao, Yuxin ; Ren, Siyu ; Hou, Junhui et al. / DynoSurf : Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction. Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXXIII. editor / Aleš Leonardis ; Elisa Ricci ; Stefan Roth ; Olga Russakovsky ; Torsten Sattler ; Gül Varol. Springer, Cham, 2024. pp. 271-288 (Lecture Notes in Computer Science).

@inproceedings{7ef4fb7736f948409173a7c6d49d7e3f,

title = "DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction",

abstract = "This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf. {\textcopyright} 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG 2025",

keywords = "Dynamic Surface Reconstruction, Temporally Consistent Meshes, Low-Dimensional Deformation, Point Cloud Sequences",

author = "Yuxin Yao and Siyu Ren and Junhui Hou and Zhi Deng and Juyong Zhang and Wenping Wang",

note = "Research Unit(s) information for this publication is provided by the author(s) concerned. ; 18th European Conference on Computer Vision (ECCV 2024), ECCV2024 ; Conference date: 29-09-2024 Through 04-10-2024",

year = "2024",

month = oct,

day = "25",

doi = "10.1007/978-3-031-73414-4_16",

language = "English",

isbn = "978-3-031-73413-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "271--288",

editor = "Ale{\v s} Leonardis and Elisa Ricci and Stefan Roth and Olga Russakovsky and Torsten Sattler and G{\"u}l Varol",

booktitle = "Computer Vision – ECCV 2024",

url = "https://eccv.ecva.net/",

}

Yao, Y, Ren, S , Hou, J, Deng, Z, Zhang, J & Wang, W 2024, DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction. in A Leonardis, E Ricci, S Roth, O Russakovsky, T Sattler & G Varol (eds), Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXXIII. Lecture Notes in Computer Science, vol. 15091, Springer, Cham, pp. 271-288, 18th European Conference on Computer Vision (ECCV 2024), Milan, Italy, 29/09/24. https://doi.org/10.1007/978-3-031-73414-4_16

DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction. / Yao, Yuxin; Ren, Siyu ; Hou, Junhui et al.
Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXXIII. ed. / Aleš Leonardis; Elisa Ricci; Stefan Roth; Olga Russakovsky; Torsten Sattler; Gül Varol. Springer, Cham, 2024. p. 271-288 (Lecture Notes in Computer Science; Vol. 15091).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - DynoSurf

T2 - 18th European Conference on Computer Vision (ECCV 2024)

AU - Yao, Yuxin

AU - Ren, Siyu

AU - Hou, Junhui

AU - Deng, Zhi

AU - Zhang, Juyong

AU - Wang, Wenping

N1 - Research Unit(s) information for this publication is provided by the author(s) concerned.

PY - 2024/10/25

Y1 - 2024/10/25

N2 - This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf. © 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG 2025

AB - This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf. © 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG 2025

KW - Dynamic Surface Reconstruction

KW - Temporally Consistent Meshes

KW - Low-Dimensional Deformation

KW - Point Cloud Sequences

UR - https://www.scopus.com/pages/publications/105018220445

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105018220445&origin=recordpage

U2 - 10.1007/978-3-031-73414-4_16

DO - 10.1007/978-3-031-73414-4_16

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-3-031-73413-7

T3 - Lecture Notes in Computer Science

SP - 271

EP - 288

BT - Computer Vision – ECCV 2024

A2 - Leonardis, Aleš

A2 - Ricci, Elisa

A2 - Roth, Stefan

A2 - Russakovsky, Olga

A2 - Sattler, Torsten

A2 - Varol, Gül

PB - Springer, Cham

Y2 - 29 September 2024 through 4 October 2024

ER -

Yao Y, Ren S , Hou J, Deng Z, Zhang J, Wang W. DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction. In Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G, editors, Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXXIII. Springer, Cham. 2024. p. 271-288. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-73414-4_16

DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction

Abstract

Publication series

Conference

Bibliographical note

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Empowering Deep Modeling of 3D Point Clouds with 2D Visual Modalities

GRF: Deep Regular Geometry Representations for 3D Point Cloud Processing

GRF: Learning-based Three-dimensional Point Cloud Data Reconstruction and Processing

Cite this

DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction

Abstract

Publication series

Conference

Bibliographical note

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Empowering Deep Modeling of 3D Point Clouds with 2D Visual Modalities

GRF: Deep Regular Geometry Representations for 3D Point Cloud Processing

GRF: Learning-based Three-dimensional Point Cloud Data Reconstruction and Processing

Cite this