publications
2026
- arXiv: Preprint 2026 New
LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image
* Equal contribution
Reconstructs a person and the object they interact with from one image, using dense proximity fields and a learned interaction prior.
BibTeX@article{antic2026lexis, title = {{LEXIS}: {LatEnt} {ProXimal} Interaction Signatures for {3D} {HOI} from an Image}, author = {Anti\'{c}, Dimitrije and Budria*, Alvaro and Paschalidis*, Georgios and Dwivedi, Sai Kumar and Tzionas, Dimitrios}, journal = {arXiv preprint arXiv:2604.20800}, year = {2026}, }
2025
- ICCV: IEEE/CVF International Conference on Computer Vision 2025
SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image
Recovers an object’s 3D pose and shape from one image by fitting a morphable signed distance function.
BibTeX@inproceedings{antic2025sdfit, title = {{SDFit}: {3D} Object Pose and Shape by Fitting a Morphable {SDF} to a Single Image}, author = {Anti\'{c}, Dimitrije and Paschalidis, Georgios and Tripathi, Shashank and Gevers, Theo and Dwivedi, Sai Kumar and Tzionas, Dimitrios}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = oct, year = {2025}, } - CVPR: IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025
InteractVLM: 3D Interaction Reasoning from 2D Foundational Models
Predicts 3D human–object contact by lifting the reasoning of 2D vision-language models into 3D.
BibTeX@inproceedings{dwivedi_interactvlm_2025, title = {{InteractVLM}: {3D} Interaction Reasoning from {2D} Foundational Models}, author = {Dwivedi, Sai Kumar and Anti\'{c}, Dimitrije and Tripathi, Shashank and Taheri, Omid and Schmid, Cordelia and Black, Michael J. and Tzionas, Dimitrios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = jun, year = {2025}, } - 3DV: International Conference on 3D Vision 2025
3D Whole-Body Grasp Synthesis with Directional Controllability
Generates whole-body grasps for a given object with control over the approach direction.
BibTeX@inproceedings{paschalidis2025cwgrasp, title = {{3D} {W}hole-Body Grasp Synthesis with Directional Controllability}, author = {Paschalidis, Georgios and Wilschut, Romana and Anti\'{c}, Dimitrije and Taheri, Omid and Tzionas, Dimitrios}, booktitle = {{International Conference on 3D Vision (3DV)}}, year = {2025}, month = mar, }
2024
- 3DV: International Conference on 3D Vision 2024
CloSe: A 3D Clothing Segmentation Dataset and Model
A dataset and model for segmenting clothing on 3D scans of people.
BibTeX@inproceedings{antic2024close, title = {CloSe: A 3D Clothing Segmentation Dataset and Model}, author = {Anti\'{c}, Dimitrije and Tiwari, Garvita and Ozcomlekci, Batuhan and Marin, Riccardo and Pons-Moll, Gerard}, booktitle = {International Conference on 3D Vision (3DV)}, month = mar, year = {2024}, }
2022
- ECCV: European Conference on Computer Vision 2022
Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields
Models the manifold of valid human poses as a neural distance field.
Best Paper Honorable Mention
BibTeX@inproceedings{tiwari22posendf, author = {Tiwari, Garvita and Anti\'{c}, Dimitrije and Lenssen, Jan Eric and Sarafianos, Nikolaos and Tung, Tony and Pons-Moll, Gerard}, booktitle = {European Conference on Computer Vision (ECCV)}, month = oct, title = {Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields}, year = {2022}, } - ICLR: International Conference on Learning Representations 2022
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
Shows why heteroscedastic uncertainty estimation fails in practice and proposes a simple fix.
BibTeX@inproceedings{Seitzer2022PitfallsOfUncertainty, author = {Seitzer, Maximilian and Tavakoli, Arash and Antic, Dimitrije and Martius, Georg}, booktitle = {International Conference on Learning Representations}, month = apr, publisher = {arXiv}, title = {On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks}, year = {2022}, }
