Adversarial learning for unguided single depth map completion of indoor scenes
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.
Code (1)
Similar Papers 제목 키워드 기반
A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion
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+2ETA: Energy-based Test-time Adaptation for Depth Completion
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 CompletionDeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image
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 PredictionSelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments
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 CompletionNeed for Speed: Zero-Shot Depth Completion with Single-Step Diffusion
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