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.
Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion
CDGS: Confidence-Aware Depth Regularization for 3D Gaussian Splatting
Challenges of Multi-Modal Coreset Selection for Depth Prediction
SHADeS: Self-supervised Monocular Depth Estimation Through Non-Lambertian Image Decomposition
Pre-training Auto-regressive Robotic Models with 4D Representations
Deep Neural Networks for Accurate Depth Estimation with Latent Space Features
pySLAM: An Open-Source, Modular, and Extensible Framework for SLAM
Adjust Your Focus: Defocus Deblurring From Dual-Pixel Images Using Explicit Multi-Scale Cross-Correlation
RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control
CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
S$^2$-Diffusion: Generalizing from Instance-level to Category-level Skills in Robot Manipulation
SteROI-D: System Design and Mapping for Stereo Depth Inference on Regions of Interest
Learning Inverse Laplacian Pyramid for Progressive Depth Completion
Extended monocular 3D imaging
Matrix3D: Large Photogrammetry Model All-in-One
Fully Exploiting Vision Foundation Model's Profound Prior Knowledge for Generalizable RGB-Depth Driving Scene Parsing
From Image to Video: An Empirical Study of Diffusion Representations
SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
Building Rome with Convex Optimization
MetaFE-DE: Learning Meta Feature Embedding for Depth Estimation from Monocular Endoscopic Images
DOC-Depth: A novel approach for dense depth ground truth generation
Leveraging Stable Diffusion for Monocular Depth Estimation via Image Semantic Encoding
Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion
Snapshot Compressed Imaging Based Single-Measurement Computer Vision for Videos
Rethinking Encoder-Decoder Flow Through Shared Structures
PromptMono: Cross Prompting Attention for Self-Supervised Monocular Depth Estimation in Challenging Environments
IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models
Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks
UniUIR: Considering Underwater Image Restoration as An All-in-One Learner
Survey on Monocular Metric Depth Estimation
Fast Underwater Scene Reconstruction using Multi-View Stereo and Physical Imaging
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-time Sparse-View 3D Rendering
FoundationStereo: Zero-Shot Stereo Matching
Multi-Modal Attention Networks for Enhanced Segmentation and Depth Estimation of Subsurface Defects in Pulse Thermography
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.