paper-with-me

홈 › Papers

Adversarial learning for unguided single depth map completion of indoor scenes

2025-01-07 · Machine Vision and Applications 2025 1 · Moushumi Medhi, Rajiv Ranjan Sahay

Depth map completion without guidance from color images is a challenging, ill-posed problem. Conventional methods rely on computationally intensive optimization processes. This work proposes a deep adversarial learning approach to estimate missing depth information directly from a single degraded observation, without requiring RGB guidance or postprocessing.

📄 PDF Abstract BibTeX

Code (1)

Moushumi9medhi/Depth-Completion pytorch

Similar Papers 제목 키워드 기반

A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion

2024-06-14 · Kailai Sun, Zhou Yang, Qianchuan Zhao

Depth images have a wide range of applications, such as 3D reconstruction, autonomous driving, augmented reality, robot navigation, and scene understanding. Commodity-grade depth cameras are hard to sense depth for brigh…

3D ReconstructionAutonomous DrivingDecoderDepth Completion+2

ETA: Energy-based Test-time Adaptation for Depth Completion

2025-08-08 · Younjoon Chung, Hyoungseob Park, Patrick Rim, Xiaoran Zhang 외 arxiv

We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some ``source'' data, often predict erroneous outputs when transferred to ``target'' data captured i…

Test-time AdaptationDepth Completion

DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image

2018-12-02 · CVPR 2019 6 · Jiaxiong Qiu, Zhaopeng Cui, yinda zhang, Xingdi Zhang 외

In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor depth completion, our network estimates…

DecoderDepth CompletionDepth EstimationDepth Prediction

SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments

2020-11-10 · Jaehoon Choi, Dongki Jung, Yonghan Lee, Deokhwa Kim 외

We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences wit…

Depth Completion

Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion

2026-03-11 · Jakub Gregorek, Paraskevas Pegios, Nando Metzger, Konrad Schindler 외 arxiv

We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typically associated with diffusion-based method…

Domain GeneralizationDepth Completion