Imagen de Portada

Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jesslen, Artur, Dünkel, Olaf, Kortylewski, Adam
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

Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
por: Sommer, Leonhard, et al.
Publicado: (2026)

CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts
por: Dünkel, Olaf, et al.
Publicado: (2025)

SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
por: Dünkel, Olaf, et al.
Publicado: (2026)

Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels
por: Dünkel, Olaf, et al.
Publicado: (2025)

Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos
por: Sommer, Leonhard, et al.
Publicado: (2024)

Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space
por: Sommer, Leonhard, et al.
Publicado: (2025)

Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
por: Pham, Nhi, et al.
Publicado: (2025)

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
por: Begiristain, León, et al.
Publicado: (2026)

NOVUM: Neural Object Volumes for Robust Object Classification
por: Jesslen, Artur, et al.
Publicado: (2023)

iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
por: Fischer, Tom, et al.
Publicado: (2024)

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data
por: Liu, Qihao, et al.
Publicado: (2024)

FaceGPT: Self-supervised Learning to Chat about 3D Human Faces
por: Wang, Haoran, et al.
Publicado: (2024)

Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects
por: Sommer, Leonhard, et al.
Publicado: (2026)

Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling
por: Dünkel, Olaf, et al.
Publicado: (2024)

Learning Human Visual Attention on 3D Surfaces through Geometry-Queried Semantic Priors
por: Pahari, Soham, et al.
Publicado: (2026)

Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
por: Wang, Xingrui, et al.
Publicado: (2024)

DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
por: Chi, Yu, et al.
Publicado: (2023)

Hierarchical Neural Semantic Representation for 3D Semantic Correspondence
por: Du, Keyu, et al.
Publicado: (2025)

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
por: Zhang, Junyi, et al.
Publicado: (2023)

PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views
por: Shi, Jiaxin, et al.
Publicado: (2026)

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
por: Xu, Jiacong, et al.
Publicado: (2023)

Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning
por: Duan, Ruxiao, et al.
Publicado: (2023)

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
por: Ma, Wufei, et al.
Publicado: (2024)

Sample-Specific Output Constraints for Neural Networks
por: Brosowsky, Mathis, et al.
Publicado: (2020)

Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models
por: Wang, Qian, et al.
Publicado: (2024)

3x2: 3D Object Part Segmentation by 2D Semantic Correspondences
por: Thai, Anh, et al.
Publicado: (2024)

Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors
por: Chen, Minglin, et al.
Publicado: (2025)

A Bayesian Approach to OOD Robustness in Image Classification
por: Kaushik, Prakhar, et al.
Publicado: (2024)

3D Multi-View Stylization with Pose-Free Correspondences Matching for Robust 3D Geometry Preservation
por: Bose, Shirsha
Publicado: (2026)

Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence
por: Cadar, Felipe, et al.
Publicado: (2024)

Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation
por: Xu, Chongyang, et al.
Publicado: (2026)

PointSt3R: Point Tracking through 3D Grounded Correspondence
por: Guerrier, Rhodri, et al.
Publicado: (2025)

Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform
por: Park, Chunghyun, et al.
Publicado: (2024)

Independently Keypoint Learning for Small Object Semantic Correspondence
por: Jin, Hailong, et al.
Publicado: (2024)

Unleashing Semantic and Geometric Priors for 3D Scene Completion
por: Chen, Shiyuan, et al.
Publicado: (2025)

GS4Buildings: Prior-Guided Gaussian Splatting for 3D Building Reconstruction
por: Zhang, Qilin, et al.
Publicado: (2025)

General Neural Gauge Fields
por: Zhan, Fangneng, et al.
Publicado: (2023)

Emergent Extreme-View Geometry in 3D Foundation Models
por: Zhang, Yiwen, et al.
Publicado: (2025)

SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
por: Yoon, Soyeon, et al.
Publicado: (2026)

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting
por: Lu, Yiren, et al.
Publicado: (2026)