FlowFormer: A Transformer Architecture for Optical Flow
FlowFormer: A Transformer Architecture for Optical Flow
Zhaoyang Huang,Xiaoyu Shi,5 Authors,Hongsheng Li
TLDR
This work introduces optical Flow transFormer, a transformer-based neural network architecture for learning optical flow that tokenizes the 4D cost volume built from an image pair, encodes the cost tokens into a cost memory with alternate-group transformer layers in a novel latent space, and decode the cost memory via a recurrent transformer decoder with dynamic positional cost queries.
Abstract
We introduce optical Flow transFormer, dubbed as FlowFormer, a transformer-based neural network architecture for learning optical flow. FlowFormer tokenizes the 4D cost volume built from an image pair, encodes the cost tokens into a cost memory with alternate-group transformer (AGT) layers in a novel latent space, and decodes the cost memory via a recurrent transformer decoder with dynamic positional cost queries. On the Sintel benchmark, FlowFormer achieves 1.159 and 2.088 average end-point-error (AEPE) on the clean and final pass, a 16.5% and 15.5% error reduction from the best published result (1.388 and 2.47). Besides, FlowFormer also achieves strong generalization performance. Without being trained on Sintel, FlowFormer achieves 1.01 AEPE on the clean pass of Sintel training set, outperforming the best published result (1.29) by 21.7%.