US 12,293,548 B2
Systems and methods for estimating scaled maps by sampling representations from a learning model
Vitor Campagnolo Guizilini, Santa Clara, CA (US); Igor Vasiljevic, San Mateo, CA (US); Dian Chen, San Jose, CA (US); Adrien David Gaidon, San Jose, CA (US); and Rares A. Ambrus, San Francisco, CA (US)
Assigned to Toyota Research Institute, Inc., Los Altos, CA (US); and Toyota Jidosha Kabushiki Kaisha, Toyota (JP)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US)
Filed on Oct. 13, 2023, as Appl. No. 18/486,619.
Claims priority of provisional application 63/461,014, filed on Apr. 21, 2023.
Prior Publication US 2024/0354991 A1, Oct. 24, 2024
Int. Cl. G06T 7/80 (2017.01); G06T 7/50 (2017.01)
CPC G06T 7/80 (2017.01) [G06T 7/50 (2017.01); G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An estimation system comprising:
a memory storing instructions that, when executed by a processor, cause the processor to:
encode data embeddings by a learning model to form conditioned latent representations using attention networks, the data embeddings including features about an image from a camera and calibration information about the camera;
compute a probability distribution of the conditioned latent representations by factoring scale priors;
sample the probability distribution to generate variations for the data embeddings; and
estimate scaled depth maps of a scene from the variations at different coordinates using the attention networks.