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.
Generalizing monocular colonoscopy image depth estimation by uncertainty-based global and local fusion network
DepthART: Monocular Depth Estimation as Autoregressive Refinement Task
FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera
@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction
DAP-LED: Learning Degradation-Aware Priors with CLIP for Joint Low-light Enhancement and Deblurring
SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending
Interpretable Action Recognition on Hard to Classify Actions
Panoptic-Depth Forecasting
Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
DiffFAS: Face Anti-Spoofing via Generative Diffusion Models
Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage
FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments
Advancing Depth Anything Model for Unsupervised Monocular Depth Estimation in Endoscopy
Real-time Multi-view Omnidirectional Depth Estimation System for Robots and Autonomous Driving on Real Scenes
LED: Light Enhanced Depth Estimation at Night
Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor
EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation
Constructive Universal Approximation and Finite Sample Memorization by Narrow Deep ReLU Networks
EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy Labels
TanDepth: Leveraging Global DEMs for Metric Monocular Depth Estimation in UAVs
Introducing a Class-Aware Metric for Monocular Depth Estimation: An Automotive Perspective
Estimating Indoor Scene Depth Maps from Ultrasonic Echoes
GGS: Generalizable Gaussian Splatting for Lane Switching in Autonomous Driving
Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization
Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation
SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction
UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching
Skip-and-Play: Depth-Driven Pose-Preserved Image Generation for Any Objects
iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation
MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.