Imagen de Portada

Learn Your Scales: Towards Scale-Consistent Generative Novel View Synthesis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Forghani, Fereshteh, Yu, Jason J., Aumentado-Armstrong, Tristan, Derpanis, Konstantinos G., Brubaker, Marcus A.
Formato:	Preprint
Publicado:	2025
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

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

Geometry-Aware Diffusion Models for Multiview Scene Inpainting
por: Salimi, Ahmad, et al.
Publicado: (2025)

Watch Your Steps: Local Image and Scene Editing by Text Instructions
por: Mirzaei, Ashkan, et al.
Publicado: (2023)

Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
por: Kazerouni, Amirhossein, et al.
Publicado: (2026)

BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors
por: Huo, Dong, et al.
Publicado: (2026)

Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution
por: Ren, Weiming, et al.
Publicado: (2025)

Can Generative Models Improve Self-Supervised Representation Learning?
por: Ayromlou, Sana, et al.
Publicado: (2024)

Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models
por: Kowal, Matthew, et al.
Publicado: (2024)

Augmenting Perceptual Super-Resolution via Image Quality Predictors
por: Zhang, Fengjia, et al.
Publicado: (2025)

Generative Point Tracking with Flow Matching
por: Tesfaldet, Mattie, et al.
Publicado: (2025)

Probabilistic Directed Distance Fields for Ray-Based Shape Representations
por: Aumentado-Armstrong, Tristan, et al.
Publicado: (2024)

Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis
por: Nguyen, Thang-Anh-Quan, et al.
Publicado: (2025)

Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks
por: Kumar, Abhinav, et al.
Publicado: (2025)

On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
por: Meuleman, Andreas, et al.
Publicado: (2025)

XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold
por: Wang, Guangyu, et al.
Publicado: (2024)

NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation
por: Jeong, Mingyu, et al.
Publicado: (2025)

NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods
por: Kulhanek, Jonas, et al.
Publicado: (2024)

Scaling View Synthesis Transformers
por: Kim, Evan, et al.
Publicado: (2026)

NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis
por: You, Zinuo, et al.
Publicado: (2023)

CheapNVS: Real-Time On-Device Narrow-Baseline Novel View Synthesis
por: Georgiadis, Konstantinos, et al.
Publicado: (2025)

Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data
por: Nair, Nithin Gopalakrishnan, et al.
Publicado: (2025)

MultiDiff: Consistent Novel View Synthesis from a Single Image
por: Müller, Norman, et al.
Publicado: (2024)

Ctrl123: Consistent Novel View Synthesis via Closed-Loop Transcription
por: Zhao, Hongxiang, et al.
Publicado: (2024)

WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image
por: Park, Jiwoo, et al.
Publicado: (2025)

MegaScenes: Scene-Level View Synthesis at Scale
por: Tung, Joseph, et al.
Publicado: (2024)

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

HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis
por: Teufel, Timo, et al.
Publicado: (2025)

GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo
por: Vats, Vibhas K., et al.
Publicado: (2023)

Towards Consistent Long-Term Pose Generation
por: Li, Yayuan, et al.
Publicado: (2025)

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling
por: Zhou, Chao, et al.
Publicado: (2025)

Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
por: Peng, Rui, et al.
Publicado: (2024)

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

FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
por: Jiang, Chenhan, et al.
Publicado: (2026)

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
por: Thasarathan, Harrish, et al.
Publicado: (2025)

Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
por: Han, Liang, et al.
Publicado: (2024)

Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks
por: Kowal, Matthew, et al.
Publicado: (2022)

Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation
por: Liu, Hongli, et al.
Publicado: (2026)

BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting
por: Wu, Yongchang, et al.
Publicado: (2025)

Go with Your Gut: Scaling Confidence for Autoregressive Image Generation
por: Chen, Harold Haodong, et al.
Publicado: (2025)

CMC: Few-shot Novel View Synthesis via Cross-view Multiplane Consistency
por: Zhu, Hanxin, et al.
Publicado: (2024)