Preprint
Aug 2026
XDG: Accelerated Visual Disambiguation
XDG is introduced, an efficient visual disambiguation model designed for scalable SfM that remains competitive with the state-of-the-art disambiguation method across pairwise and reconstruction benchmarks and delivers more than a 3x inference speedup.
Gonglin Chen, Ben Southall, Hanyuan Xiao et al.
· 0 citations