Dmitry Petrov

Dmitry Petrov

Auto-generated profile, based on publicly available information

Dmitry Petrov

University of Massachusetts Amherst, United States of America

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
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.

13 July 2024
Verified
Conference Paper
Open access
DPDmitry Petrov
Dmitry Petrov
PGPradyumn Goyal
Pradyumn Goyal
VTVikas Thamizharasan
Vikas Thamizharasan
VKVladimir Kim
Vladimir Kim
MGMatheus Gadelha
Matheus Gadelha
EKEvangelos Kalogerakis
Evangelos Kalogerakis
We introduce GEM3D 1 – a new deep, topology-aware generative model of 3D shapes. The key ingredient of our method is a neural skeleton-based representation encoding information on both shape topology and geometry. Through a denoising diffusion probabilistic model, our method first generates skeleton-based representations following the Medial Axis Transform (MAT), then generates surfaces through a skeleton-driven neural implicit formulation. The neural implicit takes into account the topological and geometric information stored in the generated skeleton representations to yield surfaces that are more topologically and geometrically accurate compared to previous neural field formulations. We discuss applications of our method in shape synthesis and point cloud reconstruction tasks, and evaluate our method both qualitatively and quantitatively. We demonstrate significantly more faithful surface reconstruction and diverse shape generation results compared to the state-of-the-art, also involving challenging scenarios of reconstructing and synthesizing structurally complex, high-genus shape surfaces from Thingi10K and ShapeNet.

10 August 2023 in Computer Graphics Forum
Verified
Journal Article
Open access
MLMarios Loizou
Marios Loizou
SGSiddhant Garg
Siddhant Garg
DPDmitry Petrov
Dmitry Petrov
MAMelinos Averkiou
Melinos Averkiou
EKEvangelos Kalogerakis
Evangelos Kalogerakis
We present a deep learning method that propagates point‐wise feature representations across shapes within a collection for the purpose of 3D shape segmentation. We propose a cross‐shape attention mechanism to enable interactions between a shape's point‐wise features and those of other shapes. The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point‐wise feature representations for shape segmentation. Our method also proposes a shape retrieval measure to select suitable shapes for cross‐shape attention operations for each test shape. Our experiments demonstrate that our approach yields state‐of‐the‐art results in the popular PartNet dataset.