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.
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Large Language Models Can Understanding Depth from Monocular Images
GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsampling
Disparity Estimation Using a Quad-Pixel Sensor
UDGS-SLAM : UniDepth Assisted Gaussian Splatting for Monocular SLAM
Synthetic Lunar Terrain: A Multimodal Open Dataset for Training and Evaluating Neuromorphic Vision Algorithms
Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method
DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model
Revisiting 360 Depth Estimation with PanoGabor: A New Fusion Perspective
EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More
Time-Aware Face Anti-Spoofing with Rotation Invariant Local Binary Patterns and Deep Learning
Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack
Depth Restoration of Hand-Held Transparent Objects for Human-to-Robot Handover
Pixel-Aligned Multi-View Generation with Depth Guided Decoder
NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth
TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers
Re-evaluation of Face Anti-spoofing Algorithm in Post COVID-19 Era Using Mask Based Occlusion Attack
Sapiens: Foundation for Human Vision Models
CatFree3D: Category-agnostic 3D Object Detection with Diffusion
LiFCal: Online Light Field Camera Calibration via Bundle Adjustment
P3P: Pseudo-3D Pre-training for Scaling 3D Voxel-based Masked Autoencoders
SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition
Structure-preserving Image Translation for Depth Estimation in Colonoscopy Video
Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling
G$^2$V$^2$former: Graph Guided Video Vision Transformer for Face Anti-Spoofing
Detecting Car Speed using Object Detection and Depth Estimation: A Deep Learning Framework
Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimation
Focal Depth Estimation: A Calibration-Free, Subject- and Daytime Invariant Approach
BodySLAM: A Generalized Monocular Visual SLAM Framework for Surgical Applications
Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining
Gaussian Mixture based Evidential Learning for Stereo Matching
MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas
Embodiment: Self-Supervised Depth Estimation Based on Camera Models
High-Precision Self-Supervised Monocular Depth Estimation with Rich-Resource Prior
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.