all AI news
RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers. (arXiv:2203.13296v2 [cs.CV] UPDATED)
Aug. 29, 2022, 1:14 a.m. | Michał J. Tyszkiewicz, Kevis-Kokitsi Maninis, Stefan Popov, Vittorio Ferrari
cs.CV updates on arXiv.org arxiv.org
We propose a transformer-based neural network architecture for multi-object
3D reconstruction from RGB videos. It relies on two alternative ways to
represent its knowledge: as a global 3D grid of features and an array of
view-specific 2D grids. We progressively exchange information between the two
with a dedicated bidirectional attention mechanism. We exploit knowledge about
the image formation process to significantly sparsify the attention weight
matrix, making our architecture feasible on current hardware, both in terms of
memory and computation. …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote