AdaptSplat adds a lightweight Frequency-Preserving Adapter to vision foundation models that extracts direction-aware high-frequency priors and integrates them via positional encodings and residual modulation to improve feed-forward 3D Gaussian Splatting fidelity and cross-domain performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting
AdaptSplat adds a lightweight Frequency-Preserving Adapter to vision foundation models that extracts direction-aware high-frequency priors and integrates them via positional encodings and residual modulation to improve feed-forward 3D Gaussian Splatting fidelity and cross-domain performance.