Voxel-based approaches are today’s standard to encode volume data. Recently, directed acyclic graphs (DAGs) were successfully used for compression, but they are restricted to a single bit of (geometry) information per voxel. We present several methods to compress arbitrary data (e.g., colors, normals, or reflectance information). Our most successful method decouples geometry and voxel data via a novel mapping scheme, enabling us to apply the DAG principle on the geometry while compressing the voxel attributes using a specialized algorithm. This leads to a drastic memory reduction. Our method outperforms existing state-of-the-art techniques and is well-suited for GPU architectures, resulting in real-time performance on commodity hardware for...
International audienceWe present two learning-based methods for coding point clouds geometry. The tw...
This paper presents a new approach for the voxelization of volumetric scene graphs. The algorithm ge...
This thesis investigates a memory-efficient representation of highly detailed geometry in 3D voxel g...
Voxels are a popular choice to encode complex geometry. Their regularity makes updates easy and enab...
Representing geometry data as voxels allows for a massive amount of detail that can be rendered in r...
Sparse Voxel Directed Acyclic Graphs (SVDAGs) are an efficient solution for storing high-resolution ...
We explore the problem of decoupling color information from geometry in large scenes of voxelized su...
We explore the problem of decoupling color information from geometry in large scenes of voxelized su...
We explore the problem of decoupling color information from geometry in large scenes of voxelized su...
Sparse Voxel Directed Acyclic Graphs (SVDAGs) losslessly compress highly detailed geometry in a high...
Sparse Voxel Directed Acyclic Graphs (SVDAGs) losslessly compress highly detailed geometry in a high...
The general shape of a 3D object can expeditiously be represented as, e.g., triangles or voxels, whi...
International audienceWe present two learning-based methods for coding point clouds geometry. The tw...
International audienceWe present two learning-based methods for coding point clouds geometry. The tw...
The paper presents and evaluates a fast graphics hardware-based voxelization method for spatial anal...
International audienceWe present two learning-based methods for coding point clouds geometry. The tw...
This paper presents a new approach for the voxelization of volumetric scene graphs. The algorithm ge...
This thesis investigates a memory-efficient representation of highly detailed geometry in 3D voxel g...
Voxels are a popular choice to encode complex geometry. Their regularity makes updates easy and enab...
Representing geometry data as voxels allows for a massive amount of detail that can be rendered in r...
Sparse Voxel Directed Acyclic Graphs (SVDAGs) are an efficient solution for storing high-resolution ...
We explore the problem of decoupling color information from geometry in large scenes of voxelized su...
We explore the problem of decoupling color information from geometry in large scenes of voxelized su...
We explore the problem of decoupling color information from geometry in large scenes of voxelized su...
Sparse Voxel Directed Acyclic Graphs (SVDAGs) losslessly compress highly detailed geometry in a high...
Sparse Voxel Directed Acyclic Graphs (SVDAGs) losslessly compress highly detailed geometry in a high...
The general shape of a 3D object can expeditiously be represented as, e.g., triangles or voxels, whi...
International audienceWe present two learning-based methods for coding point clouds geometry. The tw...
International audienceWe present two learning-based methods for coding point clouds geometry. The tw...
The paper presents and evaluates a fast graphics hardware-based voxelization method for spatial anal...
International audienceWe present two learning-based methods for coding point clouds geometry. The tw...
This paper presents a new approach for the voxelization of volumetric scene graphs. The algorithm ge...
This thesis investigates a memory-efficient representation of highly detailed geometry in 3D voxel g...