Deep Cost Ray Fusion for Sparse Depth Video Completion

2024-09-23 · Jungeon Kim, Soongjin Kim, Jaesik Park, Seungyong Lee

In this paper, we present a learning-based framework for sparse depth video completion. Given a sparse depth map and a color image at a certain viewpoint, our approach makes a cost volume that is constructed on depth hypothesis planes. To effectively fuse sequential cost volumes of the multiple viewpoints for improved depth completion, we introduce a learning-based cost volume fusion framework, namely RayFusion, that effectively leverages the attention mechanism for each pair of overlapped rays in adjacent cost volumes. As a result of leveraging feature statistics accumulated over time, our proposed framework consistently outperforms or rivals state-of-the-art approaches on diverse indoor and outdoor datasets, including the KITTI Depth Completion benchmark, VOID Depth Completion benchmark, and ScanNetV2 dataset, using much fewer network parameters.

📄 PDF Abstract BibTeX arXiv:2409.14935

Code (0)

등록된 구현이 없습니다.

Tasks

Depth Completion

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

Learning an Efficient Multimodal Depth Completion Model

2022-08-23 · Dewang Hou, Yuanyuan Du, Kai Zhao, Yang Zhao

With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems. First, the fusion of multimodal infor…

Depth Completion Depth Estimation Depth Prediction model

Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion

2024-12-18 · Massimiliano Viola, Kevin Qu, Nando Metzger, Bingxin Ke 외

Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image. Existing methods for this highly ill-posed task operate in tightly constrained settings and tend to struggle when …

Denoising Depth Completion Depth Estimation Monocular Depth Estimation+1

SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion

2025-03-03 · CVPR 2025 1 · Xuan Zhu, Jijun Xiang, Xianqi Wang, Longliang Liu 외

Lightweight direct Time-of-Flight (dToF) sensors are ideal for 3D sensing on mobile devices. However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth ma…

Depth Completion

UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completion

2022-04-16 · Guancheng Chen, Junli Lin, Huabiao Qin

Depth prediction is a critical problem in robotics applications especially autonomous driving. Generally, depth prediction based on binocular stereo matching and fusion of monocular image and laser point cloud are two ma…

Autonomous Driving Depth Completion Depth Estimation Depth Prediction+1

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints

2019-10-15 · ICCV 2019 10 · Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang 외

Depth completion aims to recover dense depth maps from sparse depth measurements. It is of increasing importance for autonomous driving and draws increasing attention from the vision community. Most of existing methods d…

Autonomous Driving Decoder Depth Completion