SOTAVerified

Monocular Depth Estimation

Monocular Depth Estimation is the task of estimating the depth value (distance relative to the camera) of each pixel given a single (monocular) RGB image. This challenging task is a key prerequisite for determining scene understanding for applications such as 3D scene reconstruction, autonomous driving, and AR. State-of-the-art methods usually fall into one of two categories: designing a complex network that is powerful enough to directly regress the depth map, or splitting the input into bins or windows to reduce computational complexity. The most popular benchmarks are the KITTI and NYUv2 datasets. Models are typically evaluated using RMSE or absolute relative error.

Source: Defocus Deblurring Using Dual-Pixel Data

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 876 papers

TitleStatusHype
SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth EstimationCode2
SelfOcc: Self-Supervised Vision-Based 3D Occupancy PredictionCode2
SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic ScenesCode2
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth EstimationCode2
Adaptive Fusion of Single-View and Multi-View Depth for Autonomous DrivingCode2
Refinement of Monocular Depth Maps via Multi-View Differentiable RenderingCode2
Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth EstimationCode2
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion PreimageCode2
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth EstimationCode2
Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth EstimationCode2
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous DrivingCode2
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVCode2
DDP: Diffusion Model for Dense Visual PredictionCode2
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth EstimationCode2
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth EstimationCode2
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image PriorsCode2
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth GenerationCode2
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene UnderstandingCode2
ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D ImagesCode2
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary CellsCode1
Feature-metric Loss for Self-supervised Learning of Depth and EgomotionCode1
A Study on the Generality of Neural Network Structures for Monocular Depth EstimationCode1
A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal EndoscopyCode1
Absolute distance prediction based on deep learning object detection and monocular depth estimation modelsCode1
Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth EstimationCode1
ENRICH: Multi-purposE dataset for beNchmaRking In Computer vision and pHotogrammetryCode1
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text AlignmentCode1
A Practical Stereo Depth System for Smart GlassesCode1
CDGS: Confidence-Aware Depth Regularization for 3D Gaussian SplattingCode1
Excavating the Potential Capacity of Self-Supervised Monocular Depth EstimationCode1
Advancing Self-supervised Monocular Depth Learning with Sparse LiDARCode1
EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth PredictionCode1
A benchmark with decomposed distribution shifts for 360 monocular depth estimationCode1
An intelligent modular real-time vision-based system for environment perceptionCode1
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised TrainingCode1
DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost VolumeCode1
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth MapsCode1
360MonoDepth: High-Resolution 360° Monocular Depth EstimationCode1
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation ModelCode1
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth EstimationCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenesCode1
RePoseD: Efficient Relative Pose Estimation With Known Depth InformationCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-LabelingCode1
Digging Into Uncertainty-based Pseudo-label for Robust Stereo MatchingCode1
Automated Distance Estimation for Wildlife Camera TrappingCode1
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection TransformersCode1
Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth EstimationCode1
Show:102550
← PrevPage 2 of 18Next →

No leaderboard results yet.