Radomir Mech

Radomir Mech

Auto-generated profile, based on publicly available information

Radomir Mech

Adobe Research

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
20 March 2014 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
OSO. Stava
O. Stava
SPS. Pirk
S. Pirk
JKJ. Kratt
J. Kratt
BCB. Chen
B. Chen
RMR. Měch
R. Měch
Bedrich BenesBedrich Benes
Bedrich Benes

26 May 2014 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
JVJ. Vanek
J. Vanek
JGJ. A. Garcia Galicia
J. A. Garcia Galicia
Bedrich BenesBedrich Benes
Bedrich Benes
RMR. Měch
R. Měch
NCN. Carr
N. Carr
GMG. S. Miller
G. S. Miller

22 July 2022 in ACM Transactions on Graphics
Verified
Journal Article
Open access
PGPaul Guerrero
Paul Guerrero
MHMiloš Hašan
Miloš Hašan
KSKalyan Sunkavalli
Kalyan Sunkavalli
RMRadomír Měch
Radomír Měch
TBTamy Boubekeur
Tamy Boubekeur
NMNiloy J. Mitra
Niloy J. Mitra
Procedural material graphs are a compact, parameteric, and resolution-independent representation that are a popular choice for material authoring. However, designing procedural materials requires significant expertise and publicly accessible libraries contain only a few thousand such graphs. We present MatFormer, a generative model that can produce a diverse set of high-quality procedural materials with complex spatial patterns and appearance. While procedural materials can be modeled as directed (operation) graphs, they contain arbitrary numbers of heterogeneous nodes with unstructured, often long-range node connections, and functional constraints on node parameters and connections. MatFormer addresses these challenges with a multi-stage transformer-based model that sequentially generates nodes, node parameters, and edges, while ensuring the semantic validity of the graph. In addition to generation, MatFormer can be used for the auto-completion and exploration of partial material graphs. We qualitatively and quantitatively demonstrate that our method outperforms alternative approaches, in both generated graph and material quality.

12 April 2017 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
JZJianming Zhang
Jianming Zhang
SMShugao Ma
Shugao Ma
MSMehrnoosh Sameki
Mehrnoosh Sameki
Stan SclaroffStan Sclaroff
Stan Sclaroff
MBMargrit Betke
Margrit Betke
RMRadomír Měch
Radomír Měch

6 April 2023 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
DPDmitry Petrov
Dmitry Petrov
MGMatheus Gadelha
Matheus Gadelha
RMRadomír Měch
Radomír Měch
EKEvangelos Kalogerakis
Evangelos Kalogerakis
We present ANISE, a method that reconstructs a 3D shape from partial observations (images or sparse point clouds) using a part-aware neural implicit shape representation. The shape is formulated as an assembly of neural implicit functions, each representing a different part instance. In contrast to previous approaches, the prediction of this representation proceeds in a coarse-to-fine manner. Our model first reconstructs a structural arrangement of the shape in the form of geometric transformations of its part instances. Conditioned on them, the model predicts part latent codes encoding their surface geometry. Reconstructions can be obtained in two ways: (i) by directly decoding the part latent codes to part implicit functions, then combining them into the final shape; or (ii) by using part latents to retrieve similar part instances in a part database and assembling them in a single shape. We demonstrate that, when performing reconstruction by decoding part representations into implicit functions, our method achieves state-of-the-art part-aware reconstruction results from both images and sparse point clouds. When reconstructing shapes by assembling parts retrieved from a dataset, our approach significantly outperforms traditional shape retrieval methods even when significantly restricting the database size. We present our results in well-known sparse point cloud reconstruction and single-view reconstruction benchmarks.

14 October 2014 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
ASA. Samii
A. Samii
RMR. Měch
R. Měch
ZLZ. Lin
Z. Lin