Papers with Code 아카이브
Depth Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 14
- 보존된 평가 기록
- 58
Depth Estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching
Improving 2D Feature Representations by 3D-Aware Fine-Tuning
Analysis and Improvement of Rank-Ordered Mean Algorithm in Single-Photon LiDAR
BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimation
Revisit Self-supervised Depth Estimation with Local Structure-from-Motion
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors
UMono: Physical Model Informed Hybrid CNN-Transformer Framework for Underwater Monocular Depth Estimation
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Enhanced Depth Estimation and 3D Geometry Reconstruction using Bayesian Helmholtz Stereopsis with Belief Propagation
Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patches
DarSwin-Unet: Distortion Aware Encoder-Decoder Architecture
ToDER: Towards Colonoscopy Depth Estimation and Reconstruction with Geometry Constraint Adaptation
Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions
SINDER: Repairing the Singular Defects of DINOv2
Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation
Many Perception Tasks are Highly Redundant Functions of their Input Data
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
GroundUp: Rapid Sketch-Based 3D City Massing
Temporally Consistent Stereo Matching
Towards Scale-Aware Full Surround Monodepth with Transformers
OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation
LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection
ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation
Generalized Face Anti-spoofing via Finer Domain Partition and Disentangling Liveness-irrelevant Factors
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning
A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation
Towards Cross-View-Consistent Self-Supervised Surround Depth Estimation
Depth-Aware Endoscopic Video Inpainting
Parametric Modeling and Estimation of Photon Registrations for 3D Imaging
Physics-Inspired Deep Learning and Transferable Models for Bridge Scour Prediction
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation
CaFNet: A Confidence-Driven Framework for Radar Camera Depth Estimation
Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.