Found 2 document(s)
Page 1 of 1
-
We investigate how frozen pretrained visual and depth representations support dense optical flow when coupled with a supervised matching network. Building on TTSFlow, this paper studies Dense Prediction Transformer (DPT)...
-
Non-rigid structure from motion (NRSfM) aims to recover camera motion and time-varying 3D shape from tracked 2D image measurements. Recent high-performing methods show that shape-space factorization remains highly effect...