Tim Elsner

Tim Elsner

Auto-generated profile, based on publicly available information

Tim Elsner

Visual Computing Institute RWTH Aachen University Germany

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2024
Verified
Book Chapter
Closed access
PDF file
TETim Elsner
Tim Elsner
JBJulia Berger
Julia Berger
TWTong Wu
Tong Wu
VCVictor Czech
Victor Czech
LGLin Gao
Lin Gao
LKLeif Kobbelt
Leif Kobbelt

30 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
TETim Elsner
Tim Elsner
VCVictor Czech
Victor Czech
JBJulia Berger
Julia Berger
ZSZain Selman
Zain Selman
ILIsaak Lim
Isaak Lim
LKLeif Kobbelt
Leif Kobbelt
Neural Radiance Fields (NeRFs) learn to represent a 3D scene from just a set of registered images. Increasing sizes of a scene demands more complex functions, typically represented by neural networks, to capture all details. Training and inference then involves querying the neural network millions of times per image, which becomes impractically slow. Since such complex functions can be replaced by multiple simpler functions to improve speed, we show that a hierarchy of Voronoi diagrams is a suitable choice to partition the scene. By equipping each Voronoi cell with its own NeRF, our approach is able to quickly learn a scene representation. We propose an intuitive partitioning of the space that increases quality gains during training by distributing information evenly among the networks and avoids artifacts through a top-down adaptive refinement. Our framework is agnostic to the underlying NeRF method and easy to implement, which allows it to be applied to various NeRF variants for improved learning and rendering speeds.

25 April 2026 in Computer Graphics Forum
Verified
Journal Article
Open access
GKGregor Kobsik
Gregor Kobsik
MHMorten Henkel
Morten Henkel
YHYanjiang He
Yanjiang He
VCVictor Czech
Victor Czech
TETim Elsner
Tim Elsner
LKLeif Kobbelt
Leif Kobbelt
The abstraction of 3D objects with simple geometric primitives like cuboids allows us to infer structural information from complex geometry. It is important for 3D shape understanding, structural analysis and geometric modeling. We introduce a novel fine‐to‐coarse self‐supervised learning approach to abstract collections of 3D shapes. Our architectural design allows us to reduce the number of primitives from hundreds (fine reconstruction) to only a few (coarse abstraction) during training. This allows our network to optimize the reconstruction error and adhere to a user‐specified number of primitives per shape while simultaneously learning a consistent structure across the whole collection of data. We achieve this through our abstraction loss formulation which increasingly penalizes redundant primitives. Furthermore, we introduce a reconstruction loss formulation to account not only for surface approximation but also volume preservation. Combining both contributions allows us to represent 3D shapes more precisely with fewer cuboid primitives than previous work. We evaluate our method on collections of man‐made and humanoid shapes comparing with previous state‐of‐the‐art learning methods on commonly used benchmarks. Our results confirm an improvement over previous cuboid‐based shape abstraction techniques. Furthermore, we demonstrate our cuboid abstraction in downstream tasks like clustering, retrieval, and partial symmetry detection.