Author

Xin Tan

h-index 13 View on Semantic Scholar

We have 2 of 67 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Scene-SAM3D: Multi-View Scene Asset Generation Without Fine-Tuning

Scene-SAM3D is introduced, a training-free framework that extends SAM3D from single-view object generation to calibrated multi-view scene asset generation, and performs step-efficient latent velocity fusion to integrate multi-view evidence and suppress cross-view conflicts in canonical space.

Yuqi Zhang, Ya-Dan Luo, Xiang-Yu Sun et al. · arXiv.org · 0 citations

Preprint Aug 2026

GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting

This work proposes GroupForward, an instance-grouped feed-forward Gaussian splatting model that reconstructs geometry, appearance, instance structure, and semantics from sparse, unposed, and uncalibrated multi-view images and proposes a Referential Scene Reasoning Framework (RSRF) for complex 3D referring segmentation.

Qi-Jian Tian, Zimeng Wu, Xu-Hong Wang et al. · 0 citations