DeepAI AI Chat
Log In Sign Up

Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization

by   Antoni Rosinol, et al.

Meshes are commonly used as 3D maps since they encode the topology of the scene while being lightweight. Unfortunately, 3D meshes are mathematically difficult to handle directly because of their combinatorial and discrete nature. Therefore, most approaches generate 3D meshes of a scene after fusing depth data using volumetric or other representations. Nevertheless, volumetric fusion remains computationally expensive both in terms of speed and memory. In this paper, we leapfrog these intermediate representations and build a 3D mesh directly from a depth map and the sparse landmarks triangulated with visual odometry. To this end, we formulate a non-smooth convex optimization problem that we solve using a primal-dual method. Our approach generates a smooth and accurate 3D mesh that substantially improves the state-of-the-art on direct mesh reconstruction while running in real-time.


page 3

page 5

page 7


An Efficient Volumetric Mesh Representation for Real-time Scene Reconstruction using Spatial Hashing

Mesh plays an indispensable role in dense real-time reconstruction essen...

Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities

Visual-Inertial Odometry (VIO) algorithms typically rely on a point clou...

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

3D shape representations that accommodate learning-based 3D reconstructi...

Reversible Harmonic Maps between Discrete Surfaces

Information transfer between triangle meshes is of great importance in c...

Probabilistic Volumetric Fusion for Dense Monocular SLAM

We present a novel method to reconstruct 3D scenes from images by levera...

Mesh-based Camera Pairs Selection and Occlusion-Aware Masking for Mesh Refinement

Many Multi-View-Stereo algorithms extract a 3D mesh model of a scene, af...

Mapping Surfaces with Earcut

Mapping a shape to some parametric domain is a fundamental tool in graph...