3 papers
cs.CV2026
Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery
Minh Kha Do, Wei Xiang, Kang Han +5
Vision-language foundation models (VLFMs) promise zero-shot and retrieval understanding for Earth observation. While operational satellite systems often lack full multi-spectral co…
cs.CV2026
GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views
Tianyu Chen, Wei Xiang, Kang Han +4
Feed-forward 3D reconstruction offers substantial runtime advantages over per-scene optimization, which remains slow at inference and often fragile under sparse views. However, exi…
cs.CV2026
SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstruction
Kang Han, Wei Xiang, Lu Yu +3
Depth-guided 3D reconstruction has gained popularity as a fast alternative to optimization-heavy approaches, yet existing methods still suffer from scale drift, multi-view inconsis…