Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors. While incorporating line features has shown clear benefits for matching and pose estimation, existing point-line approaches remain inefficient: they detect points and lines separately, use increasingly heavy network...
François Costa, Raphael Kreft, Eckhard Goedeke et al.· 0 citations
Real-world AI systems must reason about objects that are no longer visible: an AR assistant guiding a user back to an object used earlier, a household robot retrieving an item someone put away. This requires not just recalling where an object was last seen, but updating its state when it is moved and retaining that upd...
Fang-Zhou Ma, Ivo Alexander Ban, E. Homburg et al.· 0 citations
The Multimodal Floorplan Encoder (MMFE) is introduced, which maps diverse 2D indoor representations into a shared dense latent grid and improves cross-modal dense matching, enables robust similarity alignment with RANSAC, and yields strong retrieval when paired with learned aggregation.
This work proposes PolyLayout, a multi-room layout estimation method that parameterizes room layouts as Manhattan 3D polygons and optimizes them jointly across multiple rooms, and introduces two new multi-view multi-room layout benchmarks by providing layout annotations to existing datasets.
Gustav Hanning, Shao-Hui Liu, Rémi Pautrat et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
