Depth map super-resolution (DSR) has been a fundamental task for 3D computer vision. While arbitrary scale DSR is a more realistic setting in this scenario, previous approaches predominantly suffer from the issue of inefficient real-numbered scale upsampling. To explicitly address this issue, we propose a novel continuous depth representation for DSR. The heart of this representation is our proposed Geometric Spatial Aggregator (GSA), which exploits a distance field modulated by arbitrarily upsampled target gridding, through which the geometric information is explicitly introduced into feature aggregation and target generation. Furthermore, bricking with GSA, we present a transformer-style backbone named GeoDSR, which possesses a principled way to construct the functional mapping between local coordinates and the high-resolution output results, empowering our model with the advantage of arbitrary shape transformation ready to help diverse zooming demand. Extensive experimental results on standard depth map benchmarks, e.g., NYU v2, have demonstrated that the proposed framework achieves significant restoration gain in arbitrary scale depth map super-resolution compared with the prior art. Our codes are available at https://github.com/nana01219/GeoDSR.
EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration
Ningbo Global Innovation Center, Zhejiang University（浙江大学宁波全球创新中心）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；NingboTech University（宁波科技大学）；Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology, Hangzhou, China（浙江大数据与未来电子商务技术重点实验室）
Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehicles
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）；Remote Sensing and Earth Observation Laboratory, University of Copenhagen（哥本哈根大学遥感与地球观测实验室）；California PATH, University of California, Berkeley（加州大学伯克利分校加州PATH）
DET-GS: Depth- and Edge-Aware Regularization for High-Fidelity 3D Gaussian Splatting
Perceptual Imaging Laboratory (PILab), School of Electrical and Data Engineering, Faculty of Engineering and Information Technology, University of Technology Sydney（感知成像实验室（PILab）、电气与数据工程学院、工程与信息技术学院、新南威尔士大学）
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation
University of Hong Kong（香港大学）；DJI corporation（大疆创新）；Uber ATG；University of Toronto（多伦多大学）；Vector Institute（Vector研究所）；University of Oxford（牛津大学）；The Chinese University of Hong Kong（香港中文大学）
College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机科学与技术学院）；School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）
Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction
The University of Adelaide（阿德莱德大学）；Monash University（莫纳什大学）
单目深度预测在理解3D场景几何中起着至关重要的作用。虽然最近的方法已经取得了令人印象深刻的进展，如像素相对误差的评价指标，大多数方法忽略了在3D空间的几何约束。在这项工作中，我们展示了高阶3D几何约束对深度预测的重要性。通过设计一个损失项，强制执行一个简单的几何约束，即，虚拟法线方向确定随机采样的三个点在重建的三维空间，我们显着提高单目深度估计的准确性和鲁棒性。值得注意的是，虚拟法线损失不仅可以提高学习度量深度的性能，而且可以解开尺度信息，并以更好的形状信息丰富模型。因此，当无法访问绝对度量深度训练数据时，我们可以使用虚拟法线来学习在不同场景上生成的鲁棒仿射不变深度。在实验中，我们展示了在NYU Depth-V2和KITTI上学习度量深度的最新结果。根据高质量的预测深度，我们现在能够直接恢复场景的良好3D结构，例如点云和表面法线，消除了以前依赖其他模型的必要性。为了证明在具有虚拟法线损失的不同数据上学习仿射不变深度的良好通用性，我们构建了一个用于训练仿射不变深度的大规模和不同的数据集，称为Diverse Scene Depth数据集（DiverseDepth），并使用zero-shot测试设置在五个数据集上进行测试。代码可在：https://git.io/Depth
Baillie Gifford Pandemic Science Hub（巴利尔·吉福德疫情科学中心）；Institute of Regeneration and Repair（再生与修复研究所）；Heriot-Watt University（赫罗特-瓦特大学）；Institute of Photonics and Quantum Science（光子与量子科学研究所）
Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos
The Hong Kong Polytechnic University（香港理工大学）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning
Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究院）；Shanghai Institute of Intelligent Science and Technology（上海智能科学技术研究院）；Frontiers Science Center for Intelligent Autonomous Systems, Tongji University（同济大学智能自主系统前沿科学中心）
RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-time Sparse-View 3D Rendering
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；College of Biomedical Engineering and Instrument Science, Zhejiang University（浙江大学生物医学工程与仪器科学学院）；ZJU-UIUC Institute, Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合学院）
Understanding Depth and Height Perception in Large Visual-Language Models
Center for Research in Computer Vision, University of Central Florida（计算机视觉研究中心，中央佛罗里达大学）；Microsoft Research（微软研究院）；Indian Institute of Technology, Kharagpur（印度克里希纳布尔理工学院）
Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation
Princeton University（普林斯顿大学）；Springer Heidelberg（斯普林格海德堡）；ABC Institute（ABC研究所）；Aerospace Information Research Institute Chinese Academy of Sciences（中国科学院航天信息研究所）
Depth-Driven Geometric Prompt Learning for Laparoscopic Liver Landmark Detection
The Chinese University of Hong Kong（香港中文大学）；The Hong Kong Polytechnic University（香港理工大学）；Shenzhen Institute of Advanced Technology, CAS（中国科学院深圳先进技术研究院）
National Key Laboratory of Science and Technology on Multispectral Information Processing（多光谱信息处理科学技术国家重点实验室）；School of Artifical Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）
