Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to produce metric predictions. Even so, the resulting models will be geometry-specific, with …
MZ Irshad, S Zakharov, K Liu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent implicit neural representations have shown great results for novel view synthesis. However, existing methods require expensive per-scene optimization from many views …
J He, Y Wang, L Wang, H Lu, B Luo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation …
G Cha, HD Jang, D Wee - IEEE Robotics and Automation …, 2022 - ieeexplore.ieee.org
Managing the dynamic regions in the photometric loss formulation has been a main issue for handling the self-supervised depth estimation problem. Most previous methods have …
The common trade-offs of state-of-the-art methods for multi-shape representation (a single model" packing" multiple objects) involve trading modeling accuracy against memory and …
Differentiable volumetric rendering is a powerful paradigm for 3D reconstruction and novel view synthesis. However, standard volume rendering approaches struggle with degenerate …
Recent advances in deep learning have led to a data-centric intelligence ie artificially intelligent models unlocking the potential to ingest a large amount of data and be really …
TB Martins, J Civera - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
In this paper we propose the Ray-Patch querying, a novel model to efficiently query transformers to decode implicit representations into target views. Our Ray-Patch decoding …
We present WildHands, a method for 3D hand pose estimation in egocentric images in the wild. This is challenging due to (a) lack of 3D hand pose annotations for images in the wild …