collaborators

5 papers

cs.CV2026

Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction

Junhong Lin, Jinlong Wang, Xianda Guo +6

Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap. While existing methods rely on complex dec…

cs.CV2026

The Midas Touch for Metric Depth

Yu Ma, Zizhan Guo, Zuyi Xiong +5

Recent advances have markedly improved the cross-scene generalization of relative depth estimation, yet its practical applicability remains limited by the absence of metric scale,…

cs.CV2026

An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving

Yi Feng, Junwu E, Zizhan Guo +3

Panoptic occupancy prediction aims to jointly infer voxel-wise semantics and instance identities within a unified 3D scene representation. Nevertheless, progress in this field rema…

cs.CV2025

Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning

Mengtan Zhang, Zizhan Guo, Hongbo Zhao +6

Unsupervised learning of depth and ego-motion, two fundamental 3D perception tasks, has made significant strides in recent years. However, most methods treat ego-motion as an auxil…

cs.CV2025

Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching

Chuang-Wei Liu, Mingjian Sun, Cairong Zhao +3

Unsupervised stereo matching has garnered significant attention for its independence from costly disparity annotations. Typical unsupervised methods rely on the multi-view consiste…