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.
CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box Prediction
Enhanced Encoder-Decoder Architecture for Accurate Monocular Depth Estimation
Improved Depth Estimation of Bayesian Neural Networks
Depth Any Video with Scalable Synthetic Data
When Does Perceptual Alignment Benefit Vision Representations?
Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting
Color-Guided Flying Pixel Correction in Depth Images
Analysis of different disparity estimation techniques on aerial stereo image datasets
Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation
Surgical Depth Anything: Depth Estimation for Surgical Scenes using Foundation Models
CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality
Vision Transformer based Random Walk for Group Re-Identification
EndoPerfect: High-Accuracy Monocular Depth Estimation and 3D Reconstruction for Endoscopic Surgery via NeRF-Stereo Fusion
Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
Seamless Augmented Reality Integration in Arthroscopy: A Pipeline for Articular Reconstruction and Guidance
Drone Stereo Vision for Radiata Pine Branch Detection and Distance Measurement: Utilizing Deep Learning and YOLO Integration
Towards Full-parameter and Parameter-efficient Self-learning For Endoscopic Camera Depth Estimation
EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction
CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability
KineDepth: Utilizing Robot Kinematics for Online Metric Depth Estimation
fCOP: Focal Length Estimation from Category-level Object Priors
Event-based Stereo Depth Estimation: A Survey
ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts
Self-Distilled Depth Refinement with Noisy Poisson Fusion
Self-supervised Monocular Depth Estimation with Large Kernel Attention
3DDX: Bone Surface Reconstruction from a Single Standard-Geometry Radiograph via Dual-Face Depth Estimation
EventHDR: from Event to High-Speed HDR Videos and Beyond
Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation
Optical Lens Attack on Deep Learning Based Monocular Depth Estimation
Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted Data
Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results
UniBEVFusion: Unified Radar-Vision BEVFusion for 3D Object Detection
Robust and Flexible Omnidirectional Depth Estimation with Multiple 360° Cameras
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.