Enhancing Depth Completion with Multi-View Monitored Distillation
This paper presents a novel method for depth completion, which leverages multi-view improved monitored distillation to generate more precise depth maps. Our approach builds upon the state-of-the-art ensemble distillation method, in which we introduce a stereo-based model as a teacher model to improve the accuracy of the student model for depth completion. By minimizing the reconstruction error for a given image during ensemble distillation, we can avoid learning inherent error modes of completion-based teachers. To provide self-supervised information, we also employ multi-view depth consistency and multi-scale minimum reprojection. These techniques utilize existing structural constraints to yield supervised signals for student model training, without requiring costly ground truth depth information. Our extensive experimental evaluation demonstrates that our proposed method significantly improves the accuracy of the baseline monitored distillation method.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth CompletionSimilar Papers 제목 키워드 기반
A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo
In this paper, we introduce a deep multi-view stereo (MVS) system that jointly predicts depths, surface normals and per-view confidence maps. The key to our approach is a novel solver that iteratively solves for per-view…
Depth EstimationRender4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completion
We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or point clouds, we propose to use multi-v…
Image-to-Image TranslationTranslationMonitored Distillation for Positive Congruent Depth Completion
We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an …
Depth CompletionImage ReconstructionKnowledge DistillationModel SelectionEnhancing Neural Radiance Fields with Depth and Normal Completion Priors from Sparse Views
Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough image…
NeRFPatch MatchingBoosting Monocular Depth Estimation with Lightweight 3D Point Fusion
In this paper, we propose enhancing monocular depth estimation by adding 3D points as depth guidance. Unlike existing depth completion methods, our approach performs well on extremely sparse and unevenly distributed poin…
Depth CompletionDepth EstimationMonocular Depth Estimation