10 papers · 1 filter
Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach
Viktoria Ehm, Dongliang Cao, Riccardo Marin +4
Partial shape matching is a crucial yet underexplored problem in 3D vision, with significant relevance to real-world scenarios where shapes are often only partially observed. Exist…
ORMA: Optimization-based Monocular 4D Reconstruction of Articulated Animals
Xuyi Hu, Francesco Palandra, Shangzhe Wu +3
Recovering articulated 4D representations of animals from monocular videos remains challenging due to the large diversity of quadruped morphologies and lack of animal 4D supervisio…
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion
Cecilia Curreli, Florian Hofherr, Dominik Muhle +3
Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-datas…
RINO: Rotation-Invariant Non-Rigid Correspondences
Maolin Gao, Shao Jie Hu-Chen, Congyue Deng +3
Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcraf…
IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection
Johannes Meier, Florian Günther, Riccardo Marin +3
Monocular 3D detection relies on just a single camera and is therefore easy to deploy. Yet, achieving reliable 3D understanding from monocular images requires substantial annotatio…
OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata
Oussema Dhaouadi, Riccardo Marin, Johannes Meier +2
Accurate visual localization from aerial views is a fundamental problem with applications in mapping, large-area inspection, and search-and-rescue operations. In many scenarios, th…
GECO: Geometrically Consistent Embedding with Lightspeed Inference
Regine Hartwig, Dominik Muhle, Riccardo Marin +1
Recent advances in feature learning have shown that self-supervised vision foundation models can capture semantic correspondences but often lack awareness of underlying 3D geometry…
TwoSquared: 4D Generation from 2D Image Pairs
Lu Sang, Zehranaz Canfes, Dongliang Cao +3
Despite the astonishing progress in generative AI, 4D dynamic object generation remains an open challenge. With limited high-quality training data and heavy computing requirements,…
4Deform: Neural Surface Deformation for Robust Shape Interpolation
Lu Sang, Zehranaz Canfes, Dongliang Cao +3
Generating realistic intermediate shapes between non-rigidly deformed shapes is a challenging task in computer vision, especially with unstructured data (e.g., point clouds) where…
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
Cecilia Curreli, Dominik Muhle, Abhishek Saroha +3
Probabilistic human motion prediction aims to forecast multiple possible future movements from past observations. While current approaches report high diversity and realism, they o…