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 326–350 of 876 papers

TitleStatusHype
LiDAR Meta Depth CompletionCode1
OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios—0
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single ImageCode4
Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTVCode1
Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation—0
Self-supervised Monocular Depth Estimation: Let's Talk About The WeatherCode1
NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth EstimationCode1
Multi-Object Discovery by Low-Dimensional Object Motion—0
SVDM: Single-View Diffusion Model for Pseudo-Stereo 3D Object Detection—0
Towards Zero-Shot Scale-Aware Monocular Depth EstimationCode2
Cross-modal transformers for infrared and visible image fusionCode1
Continuous Online Extrinsic Calibration of Fisheye Camera and LiDAR—0
Depth and DOF Cues Make A Better Defocus Blur DetectorCode1
Lightweight Monocular Depth Estimation via Token-Sharing Transformer—0
The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation—0
A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehiclesCode1
HQDec: Self-Supervised Monocular Depth Estimation Based on a High-Quality DecoderCode0
DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth AdaptationCode1
Hierarchical Neural Memory Network for Low Latency Event ProcessingCode0
Polarimetric Imaging for Perception—0
Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance FieldsCode1
Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction—0
Learning Monocular Depth in Dynamic Environment via Context-aware Temporal Attention—0
A Multi-modal Approach to Single-modal Visual Place Classification—0
FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume—0
Show:102550
← PrevPage 14 of 36Next →

No leaderboard results yet.