mlsanityData to 14 Oct 2026

Textureless Deformable Surface Reconstruction with Invisible Markers

arXiv 2308.13678 ↗First posted 25 Aug 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Reconstructing and tracking deformable surface with little or no texture has posed long-standing challenges. Fundamentally, the challenges stem from textureless surfaces lacking features for establishing cross-image correspondences. In this work, we present a novel type of markers to proactively enrich the object's surface features, and thereby ease the 3D surface reconstruction and correspondence tracking. Our markers are made of fluorescent dyes, visible only under the ultraviolet (UV) light and invisible under regular lighting condition. Leveraging the markers, we design a multi-camera system that captures surface deformation under the UV light and the visible light in a time multiplexing fashion. Under the UV light, markers on the object emerge to enrich its surface texture, allowing high-quality 3D shape reconstruction and tracking. Under the visible light, markers become invisible, allowing us to capture the object's original untouched appearance. We perform experiments on various challenging scenes, including hand gestures, facial expressions, waving cloth, and hand-object interaction. In all these cases, we demonstrate that our system is able to produce robust, high-quality 3D reconstruction and tracking.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 72 references that are in the map. First posted on arXiv 25 Aug 2023.

Builds on

17 of 72 references.

References · 17

  1. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  2. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  3. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  4. 2023Tracking Everything Everywhere All at Oncecited by 193
  5. 2020Monocular Real-time Hand Shape and Motion Capture using Multi-modal Datacited by 106
  6. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  7. 2019DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Datacited by 77
  8. 2023Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wildcited by 36
  9. 2021Differentiable Event Stream Simulator for Non-Rigid 3D Trackingcited by 23
  10. 2019IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstructioncited by 16
  11. 2018Learning to Reconstruct Texture-less Deformable Surfaces from a Single Viewcited by 11
  12. 2023Enhancing Deformable Local Features by Jointly Learning to Detect and Describe Keypointscited by 11
5 more
  1. 2023Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Imagecited by 8
  2. 2017Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shadingcited by 6
  3. 2023ROBUSfT: Robust Real-Time Shape-from-Template, a C++ Librarycited by 6
  4. 2020A Dark Flash Normal Cameracited by 5
  5. 2016Simultaneous Surface Reflectance and Fluorescence Spectra Estimationcited by 1

Built on by

Not cited yet.