3 papers
cs.CV2026
SAMV-DUSt3R: Instance-Centric 3D Scene Decoupling from Sparse Multi-Views
Langxu Zhao, Zuan Gu, Yingdan Zhang +2
With the rising demand to decouple objects from 3D scenes, we propose SAMV-DUSt3R, an end-to-end model that injects SAM2 2D masks into MV-DUSt3R reconstruction. A Cross Flow Mask B…
cs.CV2026
GHOST: Geometry-Guided Hallucination of Opaque Surface Textures
Langxu Zhao, Zuan Gu, Tianhan Gao
Transparent objects pose a fundamental challenge for depth estimation and 3D reconstruction due to their violation of Lambertian assumptions, leading to severe geometry degradation…
cs.CV2026
ZODS-RS -- Zero-training Oriented Detection & Segmentation for Remote Sensing
Zuan Gu, Tianhan Gao, Langxu Zhao
Remote-sensing and UAV applications need models that generalize across platforms and viewpoints without task-specific training. Yet training-free pipelines often falter on oriented…