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.

Source: DIODE: A Dense Indoor and Outdoor DEpth Dataset

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Depth Estimation

논문

EgoM2P: Egocentric Multimodal Multitask Pretraining

$S^2M^2$: Scalable Stereo Matching Model for Reliable Depth Estimation

$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning

InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing

Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation

Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios

MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation

Cameras as Relative Positional Encoding

ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way

Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitions

Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation

LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures

VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting

From Pixels to Damage Severity: Estimating Earthquake Impacts Using Semantic Segmentation of Social Media Images

RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather

Underwater Monocular Metric Depth Estimation: Real-World Benchmarks and Synthetic Fine-Tuning

RoboScape: Physics-informed Embodied World Model

ThermalDiffusion: Visual-to-Thermal Image-to-Image Translation for Autonomous Navigation

StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation

THIRDEYE: Cue-Aware Monocular Depth Estimation via Brain-Inspired Multi-Stage Fusion

Look to Locate: Vision-Based Multisensory Navigation with 3-D Digital Maps for GNSS-Challenged Environments

BulletGen: Improving 4D Reconstruction with Bullet-Time Generation

Monocular One-Shot Metric-Depth Alignment for RGB-Based Robot Grasping

DreamCube: 3D Panorama Generation via Multi-plane Synchronization

EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training

RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation

DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning

TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Scale-Oriented Contrast

Self-Supervised Enhancement for Depth from a Lightweight ToF Sensor with Monocular Images

Test3R: Learning to Reconstruct 3D at Test Time

Leveraging 6DoF Pose Foundation Models For Mapping Marine Sediment Burial

DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects

Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images

Hidden in plain sight: VLMs overlook their visual representations

Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence