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.
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
UniK3D: Universal Camera Monocular 3D Estimation
QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
USAM-Net: A U-Net-based Network for Improved Stereo Correspondence and Scene Depth Estimation using Features from a Pre-trained Image Segmentation network
EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining
TULIP: Towards Unified Language-Image Pretraining
3D Densification for Multi-Map Monocular VSLAM in Endoscopy
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
Multi-view Reconstruction via SfM-guided Monocular Depth Estimation
Improving Geometric Consistency for 360-Degree Neural Radiance Fields in Indoor Scenarios
MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models
Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation
Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation
VGGT: Visual Geometry Grounded Transformer
Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
WonderVerse: Extendable 3D Scene Generation with Video Generative Models
GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing
Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
A Light and Tuning-free Method for Simulating Camera Motion in Video Generation
Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity
TomatoScanner: phenotyping tomato fruit based on only RGB image
EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images
Multi-View Depth Consistent Image Generation Using Generative AI Models: Application on Architectural Design of University Buildings
Task-Agnostic Attacks Against Vision Foundation Models
RGB-Thermal Infrared Fusion for Robust Depth Estimation in Complex Environments
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
Bridging Spectral-wise and Multi-spectral Depth Estimation via Geometry-guided Contrastive Learning
DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images
Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator
RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes
OrchardDepth: Precise Metric Depth Estimation of Orchard Scene from Monocular Camera Images
LXLv2: Enhanced LiDAR Excluded Lean 3D Object Detection with Fusion of 4D Radar and Camera
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.