Dimitrije Antić — accepted AI-conference papers

2025

InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

Sai Kumar Dwivedi, Dimitrije Antić, Shashank Tripathi, Omid Taheri, Cordelia Schmid, Michael J. Black +1

CVPR 2025poster

We introduce InteractVLM, a novel method to estimate 3D contact points on human bodies and objects from single in-the-wild images, enabling accurate human-object joint reconstruction in 3D. This is challenging due to occlusions, depth ambiguities, and widely varying object shapes. Existing methods r…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2025

SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image

Dimitrije Antić, Georgios Paschalidis, Shashank Tripathi, Theo Gevers, Sai Kumar Dwivedi, Dimitrios Tzionas

ICCV 2025poster

Recovering 3D object pose and shape from a single image is a challenging and ill-posed problem. This is due to strong (self-)occlusions, depth ambiguities, the vast intra- and inter-class shape variance, and the lack of 3D ground truth for natural images. Existing deep-network methods are trained on…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields

Garvita Tiwari, Dimitrije Antić, Jan Eric Lenssen, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll

ECCV 2022poster

"We present Pose-NDF, a continuous model for plausible human poses based on neural distance fields (NDFs). Pose or motion priors are important for generating realistic new poses and for reconstructing accurate poses from noisy or partial observations. Pose-NDF learns a manifold of plausible poses as…

Cited by 110 Source ↗PDF ↗code ↗Scholar ↗