InstanceSplat predicts 3D Gaussians with per-object identity and language-aligned semantics from unposed multi-view images in a single forward pass, enabling rendering, instance segmentation, and open-vocabulary queries.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =
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
-
InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding
InstanceSplat predicts 3D Gaussians with per-object identity and language-aligned semantics from unposed multi-view images in a single forward pass, enabling rendering, instance segmentation, and open-vocabulary queries.