PySIFT is a deterministic GPU SIFT that outperforms neural descriptor replacements on matching accuracy and geometric tasks across four benchmarks while being 2-18x faster and fully reproducible across GPU architectures.
Revisiting Oxford and Paris: Large-scale image retrieval benchmarking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines
PySIFT is a deterministic GPU SIFT that outperforms neural descriptor replacements on matching accuracy and geometric tasks across four benchmarks while being 2-18x faster and fully reproducible across GPU architectures.