Imagen de Portada

GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Yuecheng, Cheng, Junda, Liu, Longliang, Liao, Wenjing, Cheng, Hanrui, Wang, Yuzhou, Yang, Xin
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
por: Zhu, Xuan, et al.
Publicado: (2025)

PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View
por: Liu, Longliang, et al.
Publicado: (2025)

DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance
por: Xiang, Jijun, et al.
Publicado: (2025)

DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation
por: Dong, Yue-Jiang, et al.
Publicado: (2025)

MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors
por: Cheng, Junda, et al.
Publicado: (2025)

MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching
por: Feng, Miaojie, et al.
Publicado: (2023)

Learning Temporally Consistent Video Depth from Video Diffusion Priors
por: Shao, Jiahao, et al.
Publicado: (2024)

GeoSurDepth: Harnessing Foundation Model for Spatial Geometry Consistency-Oriented Self-Supervised Surround-View Depth Estimation
por: Liu, Weimin, et al.
Publicado: (2026)

SGFormer: Spherical Geometry Transformer for 360 Depth Estimation
por: Zhang, Junsong, et al.
Publicado: (2024)

IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
por: Xu, Gangwei, et al.
Publicado: (2024)

Geometry Depth Consistency in RGBD Relative Pose Estimation
por: Kumar, Sourav, et al.
Publicado: (2024)

EndoStreamDepth: Temporally Consistent Monocular Depth Estimation for Endoscopic Video Streams
por: Li, Hao, et al.
Publicado: (2025)

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
por: Chen, Sili, et al.
Publicado: (2025)

Depth3DLane: Monocular 3D Lane Detection via Depth Prior Distillation
por: Lyu, Dongxin, et al.
Publicado: (2025)

Geometry-Aware Rotary Position Embedding for Consistent Video World Model
por: Xiang, Chendong, et al.
Publicado: (2026)

Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumption
por: Feiden, Johann-Friedrich, et al.
Publicado: (2025)

No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency
por: Wu, Cho-Ying, et al.
Publicado: (2026)

FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimation
por: Wang, Fei, et al.
Publicado: (2024)

DepthFusion: Depth-Aware Hybrid Feature Fusion for LiDAR-Camera 3D Object Detection
por: Ji, Mingqian, et al.
Publicado: (2025)

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
por: Lu, Jiahao, et al.
Publicado: (2024)

Real-time Monocular Depth Estimation on Embedded Systems
por: Feng, Cheng, et al.
Publicado: (2023)

Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors
por: Zhuang, Chuanqing, et al.
Publicado: (2026)

VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation
por: Yuan, Jiayi, et al.
Publicado: (2026)

DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection
por: Liu, Yehao, et al.
Publicado: (2025)

Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry
por: Zhang, Zhaoxing, et al.
Publicado: (2024)

DCHM: Depth-Consistent Human Modeling for Multiview Detection
por: Ma, Jiahao, et al.
Publicado: (2025)

STATIC : Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation
por: Yang, Sunghun, et al.
Publicado: (2024)

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
por: Hu, Wenbo, et al.
Publicado: (2024)

SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies
por: Han, Liang, et al.
Publicado: (2025)

BoRe-Depth: Self-supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systems
por: Liu, Chang, et al.
Publicado: (2025)

See in Depth: Training-Free Surgical Scene Segmentation with Monocular Depth Priors
por: Yang, Kunyi, et al.
Publicado: (2025)

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
por: Xing, Yun, et al.
Publicado: (2025)

InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior
por: Liu, Zhiheng, et al.
Publicado: (2024)

PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency
por: Han, Leezy, et al.
Publicado: (2026)

SpatialMe: Stereo Video Conversion Using Depth-Warping and Blend-Inpainting
por: Zhang, Jiale, et al.
Publicado: (2024)

3D Gaussian Inpainting with Depth-Guided Cross-View Consistency
por: Huang, Sheng-Yu, et al.
Publicado: (2025)

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving
por: Cheng, JunDa, et al.
Publicado: (2024)

GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints
por: Cheng, Anqi, et al.
Publicado: (2024)

Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehicles
por: Liu, Weimin, et al.
Publicado: (2026)

Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video
por: Fan, Junkai, et al.
Publicado: (2024)