activity
20242026
collaborators

6 papers

cs.CV2026

LEGO: Leveled Language Gaussian Splatting

Yuning Peng, Haiping Wang, Yuan Liu +3

We introduce LEGO for advanced open-vocabulary scene understanding. Beyond basic concept recognition, its core innovation lies in capturing the intrinsic semantic hierarchies withi…

cs.CV2025

SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence

Jiabin Chen, Haiping Wang, Jinpeng Li +3

We propose SpatialLLM, a novel approach advancing spatial intelligence tasks in complex urban scenes. Unlike previous methods requiring geographic analysis tools or domain expertis…

cs.CV2025

WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Research

Jiahao Zhou, Chen Long, Yue Xie +6

End-to-end models capable of handling multiple sub-tasks in parallel have become a new trend, thereby presenting significant challenges and opportunities for the integration of mul…

cs.CV2025

GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting

Yuning Peng, Haiping Wang, Yuan Liu +3

3D open-vocabulary scene understanding, which accurately perceives complex semantic properties of objects in space, has gained significant attention in recent years. In this paper,…

cs.CV2025

ME-CPT: Multi-Task Enhanced Cross-Temporal Point Transformer for Urban 3D Change Detection

Luqi Zhang, Haiping Wang, Chong Liu +2

The point clouds collected by the Airborne Laser Scanning (ALS) system provide accurate 3D information of urban land covers. By utilizing multi-temporal ALS point clouds, semantic…

cs.CV2024

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Haiping Wang, Yuan Liu, Ziwei Liu +3

In this paper, we propose VistaDream a novel framework to reconstruct a 3D scene from a single-view image. Recent diffusion models enable generating high-quality novel-view images…