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 101–150 of 876 papers

TitleStatusHype
Enhancing Bronchoscopy Depth Estimation through Synthetic-to-Real Domain Adaptation—0
PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes—0
Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training—0
Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving—0
ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D ImagesCode2
PF3plat: Pose-Free Feed-Forward 3D Gaussian SplattingCode3
Depth Attention for Robust RGB TrackingCode1
Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared imagesCode1
DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine DomainCode1
Enhanced Encoder-Decoder Architecture for Accurate Monocular Depth EstimationCode0
Surgical Depth Anything: Depth Estimation for Surgical Scenes using Foundation Models—0
Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation—0
Vision Transformer based Random Walk for Group Re-Identification—0
EndoPerfect: High-Accuracy Monocular Depth Estimation and 3D Reconstruction for Endoscopic Surgery via NeRF-Stereo Fusion—0
Refinement of Monocular Depth Maps via Multi-View Differentiable RenderingCode2
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language DescriptionsCode0
Depth Pro: Sharp Monocular Metric Depth in Less Than a SecondCode9
EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth PredictionCode1
fCOP: Focal Length Estimation from Category-level Object Priors—0
KineDepth: Utilizing Robot Kinematics for Online Metric Depth Estimation—0
Self-supervised Monocular Depth Estimation with Large Kernel Attention—0
ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts—0
Optical Lens Attack on Deep Learning Based Monocular Depth Estimation—0
Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation—0
EventHDR: from Event to High-Speed HDR Videos and Beyond—0
Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted DataCode0
GroCo: Ground Constraint for Metric Self-Supervised Monocular DepthCode1
DepthART: Monocular Depth Estimation as Autoregressive Refinement Task—0
Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus—0
Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkCode4
Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread FunctionsCode0
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion—0
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion PreimageCode2
Advancing Depth Anything Model for Unsupervised Monocular Depth Estimation in Endoscopy—0
EDADepth: Enhanced Data Augmentation for Monocular Depth EstimationCode0
TanDepth: Leveraging Global DEMs for Metric Monocular Depth Estimation in UAVs—0
Introducing a Class-Aware Metric for Monocular Depth Estimation: An Automotive PerspectiveCode0
iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation—0
SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction—0
Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth EstimationCode2
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world VideosCode5
Large Language Models Can Understanding Depth from Monocular Images—0
DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation ModelCode1
EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More—0
Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch AttackCode0
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-trainingCode0
TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers—0
InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular DepthCode1
Structure-preserving Image Translation for Depth Estimation in Colonoscopy VideoCode1
Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling—0
Show:102550
← PrevPage 3 of 18Next →

No leaderboard results yet.