10 papers
Déjà View: Looping Transformers for Multi-View 3D Reconstruction
Alessandro Burzio, Tobias Fischer, Sven Elflein +9
Recent feed-forward 3D reconstruction transformers have scaled to over a billion parameters, following the broader trend of increasing model capacity in computer vision. Yet emergi…
Towards a Unified Copernicus Foundation Model for Earth Vision
Yi Wang, Zhitong Xiong, Chenying Liu +8
Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downs…
A Guide to Structureless Visual Localization
Vojtech Panek, Qunjie Zhou, Yaqing Ding +4
Visual localization algorithms, i.e., methods that estimate the camera pose of a query image in a known scene, are core components of many applications, including self-driving cars…
LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception
Yuan-Hong Liao, Sven Elflein, Liu He +4
Recent reasoning models through test-time scaling have demonstrated that long chain-of-thoughts can unlock substantial performance boosts in hard reasoning tasks such as math and c…
Towards Learning to Complete Anything in Lidar
Ayca Takmaz, Cristiano Saltori, Neehar Peri +4
We propose CAL (Complete Anything in Lidar) for Lidar-based shape-completion in-the-wild. This is closely related to Lidar-based semantic/panoptic scene completion. However, contem…
Zero-Shot 4D Lidar Panoptic Segmentation
Yushan Zhang, Aljoša Ošep, Laura Leal-Taixé +1
Zero-shot 4D segmentation and recognition of arbitrary objects in Lidar is crucial for embodied navigation, with applications ranging from streaming perception to semantic mapping…