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.
Generative Classifier for Domain Generalization
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
A novel gesture interaction control method for rehabilitation lower extremity exoskeleton
GaussianLSS -- Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting
FreSca: Unveiling the Scaling Space in Diffusion Models
Monocular and Generalizable Gaussian Talking Head Animation
GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
Detail-aware multi-view stereo network for depth estimation
ExScene: Free-View 3D Scene Reconstruction with Gaussian Splatting from a Single Image
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model
Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
Unsupervised Feature Disentanglement and Augmentation Network for One-class Face Anti-spoofing
Enhancing Learnable Descriptive Convolutional Vision Transformer for Face Anti-Spoofing
Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing
Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges
Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces
One Look is Enough: A Novel Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation Models on High-Resolution Images
MVSAnywhere: Zero-Shot Multi-View Stereo
EndoLRMGS: Complete Endoscopic Scene Reconstruction combining Large Reconstruction Modelling and Gaussian Splatting
ICG-MVSNet: Learning Intra-view and Cross-view Relationships for Guidance in Multi-View Stereo
Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
A Unified Image-Dense Annotation Generation Model for Underwater Scenes
Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors
Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving
Semi-SD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Driving
FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion
Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining
PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes
StableGS: A Floater-Free Framework for 3D Gaussian Splatting
Co-SemDepth: Fast Joint Semantic Segmentation and Depth Estimation on Aerial Images
GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects
Radar-Guided Polynomial Fitting for Metric Depth Estimation
Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.