7 papers · 1 filter
STAR: A Spatial-Topology Aware Routing Framework for Generalizable 3D Scene Understanding
Mingwei Xing, Xinliang Wang, Yifeng Shi
Constructing a unified 3D scene understanding model has long been hindered by the topological discrepancies across sensor modalities. While applying the Mixture-of-Experts (MoE) ar…
AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting
Mingwei Xing, Xinliang Wang, Yifeng Shi
This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply complex, architecture-specific d…
ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models
Xinliang Wang, Yifeng Shi, Zhenyu Wu
3D Gaussian Splatting (3DGS) delivers high-fidelity real-time rendering but suffers from geometric and photometric degradations under sparse-view constraints. Current generative re…
Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagery
Xinliang Wang, Yijie Kang, Zhenyu Wu +1
3D urban generation from satellite imagery is an important task for scalable digital twins and real-world simulation environments. Existing approaches primarily rely on scene-level…
DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Experts
Mingwei Xing, Xinliang Wang, Yifeng Shi
Constructing a unified 3D scene understanding model has long been hindered by the significant topological discrepancies across different sensor modalities. While applying the Mixtu…
LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
Haoran Lou, Chunxiao Fan, Ziyan Liu +2
The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for c…
ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions
Chunlong Xia, Xinliang Wang, Feng Lv +2
Although Vision Transformer (ViT) has achieved significant success in computer vision, it does not perform well in dense prediction tasks due to the lack of inner-patch information…