FastVGGT achieves 4x speedup on VGGT for 1000-image inputs using training-free token merging tailored to 3D architectures while reducing error accumulation.
Tokenlearner: Adaptive space-time tokenization for videos.Advances in neural in- formation processing systems, 34:12786–12797
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
FastVGGT achieves 4x speedup on VGGT for 1000-image inputs using training-free token merging tailored to 3D architectures while reducing error accumulation.