Copertina

From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Ranran, Luo, Weixun, Mao, Ye, Mikolajczyk, Krystian
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
di: Huang, Ranran, et al.
Pubblicazione: (2025)

SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
di: Huang, Ranran, et al.
Pubblicazione: (2025)

POMA-3D: The Point Map Way to 3D Scene Understanding
di: Mao, Ye, et al.
Pubblicazione: (2025)

Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding
di: Mao, Ye, et al.
Pubblicazione: (2026)

Hypo3D: Exploring Hypothetical Reasoning in 3D
di: Mao, Ye, et al.
Pubblicazione: (2025)

Stereo Any Video: Temporally Consistent Stereo Matching
di: Jing, Junpeng, et al.
Pubblicazione: (2025)

Lite Any Stereo: Efficient Zero-Shot Stereo Matching
di: Jing, Junpeng, et al.
Pubblicazione: (2025)

Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion
di: Kolbeinsson, Benedikt, et al.
Pubblicazione: (2022)

Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching
di: Jing, Junpeng, et al.
Pubblicazione: (2024)

OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
di: Mao, Ye, et al.
Pubblicazione: (2024)

Match Stereo Videos via Bidirectional Alignment
di: Jing, Junpeng, et al.
Pubblicazione: (2024)

UCorr: Wire Detection and Depth Estimation for Autonomous Drones
di: Kolbeinsson, Benedikt, et al.
Pubblicazione: (2025)

DDOS: The Drone Depth and Obstacle Segmentation Dataset
di: Kolbeinsson, Benedikt, et al.
Pubblicazione: (2023)

Language-Based Depth Hints for Monocular Depth Estimation
di: Auty, Dylan, et al.
Pubblicazione: (2024)

Understanding the Role of the Projector in Knowledge Distillation
di: Miles, Roy, et al.
Pubblicazione: (2023)

VI3DRM:Towards meticulous 3D Reconstruction from Sparse Views via Photo-Realistic Novel View Synthesis
di: Chen, Hao, et al.
Pubblicazione: (2024)

From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
di: Zhao, Weiguang, et al.
Pubblicazione: (2022)

RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation
di: Monteagudo, Henrique Piñeiro, et al.
Pubblicazione: (2025)

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
di: Zhang, Qi, et al.
Pubblicazione: (2024)

Comparative Analysis of Novel View Synthesis and Photogrammetry for 3D Forest Stand Reconstruction and extraction of individual tree parameters
di: Tian, Guoji, et al.
Pubblicazione: (2024)

Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesis
di: Burgdorfer, Nathaniel, et al.
Pubblicazione: (2025)

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

Learning to Project for Cross-Task Knowledge Distillation
di: Auty, Dylan, et al.
Pubblicazione: (2024)

Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis
di: Ma, Qingsen, et al.
Pubblicazione: (2025)

VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm
di: Lu, Hongbo, et al.
Pubblicazione: (2026)

True Self-Supervised Novel View Synthesis is Transferable
di: Mitchel, Thomas W., et al.
Pubblicazione: (2025)

PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction
di: Shen, Ju, et al.
Pubblicazione: (2026)

MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views
di: Li, Runfa, et al.
Pubblicazione: (2024)

OneViewAll: Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects
di: Luo, Yang, et al.
Pubblicazione: (2026)

MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis
di: Ren, Xuqian, et al.
Pubblicazione: (2023)

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

SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
di: Chen, Weiliang, et al.
Pubblicazione: (2025)

CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
di: Paliwal, Avinash, et al.
Pubblicazione: (2024)

Novel-View Acoustic Synthesis from 3D Reconstructed Rooms
di: Ahn, Byeongjoo, et al.
Pubblicazione: (2023)

Closed Loop Interactive Embodied Reasoning for Robot Manipulation
di: Nazarczuk, Michal, et al.
Pubblicazione: (2024)

ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis
di: Wang, Chuang, et al.
Pubblicazione: (2025)

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

Déjà View: Looping Transformers for Multi-View 3D Reconstruction
di: Burzio, Alessandro, et al.
Pubblicazione: (2026)

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

A Single Image and Multimodality Is All You Need for Novel View Synthesis
di: Javadi, Amirhosein, et al.
Pubblicazione: (2026)