Imagen de Portada

3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Grolleau, William, Sabourin, Astrid, Lapouge, Guillaume, Achard, Catherine
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

MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification
por: Grolleau, William, et al.
Publicado: (2026)

GaussianBeV: 3D Gaussian Representation meets Perception Models for BeV Segmentation
por: Chabot, Florian, et al.
Publicado: (2024)

View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
por: Zhang, Quan, et al.
Publicado: (2026)

SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification
por: Wang, Yuhao, et al.
Publicado: (2025)

LiftRefine: Progressively Refined View Synthesis from 3D Lifting with Volume-Triplane Representations
por: Do, Tung, et al.
Publicado: (2024)

CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis
por: Kong, Xin, et al.
Publicado: (2025)

ARSGaussian: 3D Gaussian Splatting with LiDAR for Aerial Remote Sensing Novel View Synthesis
por: Yao, Yiling, et al.
Publicado: (2024)

SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks
por: Wang, Shining, et al.
Publicado: (2025)

Aerial-Ground Image Feature Matching via 3D Gaussian Splatting-based Intermediate View Rendering
por: Yu, Jiangxue, et al.
Publicado: (2025)

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
por: Vuong, Khiem, et al.
Publicado: (2025)

Dynamic Token Selection for Aerial-Ground Person Re-Identification
por: Wang, Yuhai, et al.
Publicado: (2024)

UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images
por: Wu, Jiamin, et al.
Publicado: (2024)

Veta-GS: View-dependent deformable 3D Gaussian Splatting for thermal infrared Novel-view Synthesis
por: Nam, Myeongseok, et al.
Publicado: (2025)

LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors
por: Chen, Yabo, et al.
Publicado: (2024)

GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing
por: Wang, Yuanhao, et al.
Publicado: (2025)

LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification
por: Zhang, Pingping, et al.
Publicado: (2025)

Free3D: Consistent Novel View Synthesis without 3D Representation
por: Zheng, Chuanxia, et al.
Publicado: (2023)

MPL: Lifting 3D Human Pose from Multi-view 2D Poses
por: Ghasemzadeh, Seyed Abolfazl, et al.
Publicado: (2024)

SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion
por: Voleti, Vikram, et al.
Publicado: (2024)

Skel3D: Skeleton Guided Novel View Synthesis
por: Fóthi, Aron, et al.
Publicado: (2024)

3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance
por: Kang, Taewon, et al.
Publicado: (2024)

AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification
por: Nguyen, Huy, et al.
Publicado: (2024)

EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Multi-view Camera Settings
por: Hu, Yingdong, et al.
Publicado: (2024)

LISA-3D: Lifting Language-Image Segmentation to 3D via Multi-View Consistency
por: Guo, Zhongbin, et al.
Publicado: (2025)

Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework
por: He, Zongqi, et al.
Publicado: (2025)

HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View
por: Kothandaraman, Divya, et al.
Publicado: (2023)

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
por: T, Mukund Varma, et al.
Publicado: (2024)

GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
por: Li, Qiao, et al.
Publicado: (2025)

3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
por: Liu, Ruiqi, et al.
Publicado: (2024)

Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking
por: Van Ma, Linh, et al.
Publicado: (2024)

Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis
por: Niedermayr, Simon, et al.
Publicado: (2023)

Re-Nerfing: Improving Novel View Synthesis through Novel View Synthesis
por: Tristram, Felix, et al.
Publicado: (2023)

SnapPose3D: Diffusion-Based Single-Frame 2D-to-3D Lifting of Human Poses
por: Simoni, Alessandro, et al.
Publicado: (2026)

Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining
por: Wang, Zhumei, et al.
Publicado: (2025)

PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis
por: Yu, Jason J., et al.
Publicado: (2024)

Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
por: Min, Zhiyuan, et al.
Publicado: (2024)

Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors
por: Ungermann, Paul, et al.
Publicado: (2024)

Synthesizing Consistent Novel Views via 3D Epipolar Attention without Re-Training
por: Ye, Botao, et al.
Publicado: (2025)

ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
por: Dihlmann, Jan-Niklas, et al.
Publicado: (2026)

Open-set object detection: towards unified problem formulation and benchmarking
por: Ammar, Hejer, et al.
Publicado: (2024)