activity
20242026
collaborators

13 papers

cs.CV2026

PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations

Cheng Chi, Xianqi Wang, Hongcheng Luo +9

High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their pe…

cs.CV2026

PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences

Min Lin, Gangwei Xu, Xianqi Wang +2

Point cloud scene flow estimation is fundamental to long-term and fine-grained 3D motion analysis. However, existing methods are typically limited to pairwise settings and struggle…

cs.CV2026

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts

Xianqi Wang, Hao Yang, Hangtian Wang +4

Modern stereo matching methods have leveraged monocular depth foundation models to achieve superior zero-shot generalization performance. However, most existing methods primarily f…

cs.CV2025

Generalized Geometry Encoding Volume for Real-time Stereo Matching

Jiaxin Liu, Gangwei Xu, Xianqi Wang +2

Real-time stereo matching methods primarily focus on enhancing in-domain performance but often overlook the critical importance of generalization in real-world applications. In con…

cs.CV2025

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers

Gangwei Xu, Haotong Lin, Hongcheng Luo +11

This paper presents Pixel-Perfect Depth, a monocular depth estimation model based on pixel-space diffusion generation that produces high-quality, flying-pixel-free point clouds fro…

cs.CV2025

DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance

Jijun Xiang, Longliang Liu, Xuan Zhu +3

Depth enhancement, which converts raw dToF signals into dense depth maps using RGB guidance, is crucial for improving depth perception in high-precision tasks such as 3D reconstruc…