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 501–525 of 876 papers

TitleStatusHype
FLaME: Fast Lightweight Mesh Estimation Using Variational Smoothing on Delaunay Graphs—0
Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images—0
FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimation—0
Foundation Models Meet Low-Cost Sensors: Test-Time Adaptation for Rescaling Disparity for Zero-Shot Metric Depth Estimation—0
Fractal Pyramid Networks—0
From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior—0
From Single Images to Motion Policies via Video-Generation Environment Representations—0
FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models—0
FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scene—0
FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume—0
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation—0
GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embedding—0
Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks—0
GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR—0
GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation—0
GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding—0
Geometric Unsupervised Domain Adaptation for Semantic Segmentation—0
GIMP-ML: Python Plugins for using Computer Vision Models in GIMP—0
GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation—0
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion—0
GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal—0
GSDC Transformer: An Efficient and Effective Cue Fusion for Monocular Multi-Frame Depth Estimation—0
GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion—0
HC-Search for Structured Prediction in Computer Vision—0
Hierarchical Normalization for Robust Monocular Depth Estimation—0
Show:102550
← PrevPage 21 of 36Next →

No leaderboard results yet.