5 papers
One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking
Martin Engilberge, Ivan Vrkic, Friedrich Wilke Grosche +3
This work presents a unified, fully differentiable model for multi-people tracking that learns to associate detections into trajectories without relying on pre-computed tracklets.…
Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
Ren Li, Cong Cao, Corentin Dumery +3
Reconstructing 3D clothed humans from images is fundamental to applications like virtual try-on, avatar creation, and mixed reality. While recent advances have enhanced human body…
Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields
Corentin Dumery, Aoxiang Fan, Ren Li +2
Radiance Fields have become a powerful tool for modeling 3D scenes from multiple images. However, they remain difficult to segment into semantically meaningful regions. Some method…
AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains
Krzysztof Lis, Matthias Rottmann, Annika Mütze +3
In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this informat…
No Identity, no problem: Motion through detection for people tracking
Martin Engilberge, F. Wilke Grosche, Pascal Fua
Tracking-by-detection has become the de facto standard approach to people tracking. To increase robustness, some approaches incorporate re-identification using appearance models an…