9 papers
Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy
Yuan Wu, Zhiqiang Yan, Jiawei Lian +2
3D occupancy prediction aims to infer dense, voxel-wise scene semantics from sensor observations, where the 2D-to-3D view transformation serves as a crucial step in bridging image…
Scene Prior Filtering for Depth Super-Resolution
Zhengxue Wang, Zhiqiang Yan, Ming-Hsuan Yang +4
Multi-modal fusion serves as a cornerstone for successful depth map super-resolution. However, commonly used fusion strategies, such as addition and concatenation, fall short of ef…
SpatioTemporal Difference Network for Video Depth Super-Resolution
Zhengxue Wang, Yuan Wu, Xiang Li +2
Depth super-resolution has achieved impressive performance, and the incorporation of multi-frame information further enhances reconstruction quality. Nevertheless, statistical anal…
See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction
Yuan Wu, Zhiqiang Yan, Yigong Zhang +2
Occupancy prediction aims to estimate the 3D spatial distribution of occupied regions along with their corresponding semantic labels. Existing vision-based methods perform well on…
DuCos: Duality Constrained Depth Super-Resolution via Foundation Model
Zhiqiang Yan, Zhengxue Wang, Haoye Dong +3
We introduce DuCos, a novel depth super-resolution framework grounded in Lagrangian duality theory, offering a flexible integration of multiple constraints and reconstruction objec…
Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
Zhiqiang Yan, Zhengxue Wang, Kun Wang +2
In this paper, we introduce the Selective Image Guided Network (SigNet), a novel degradation-aware framework that transforms depth completion into depth enhancement for the first t…