Cover Image

The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Haoru, Ye, Kai, Qin, Minghan, Li, Yangyan, Chen, Wenzheng, Chen, Baoquan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images
by: Li, Lingen, et al.
Published: (2024)

4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
by: Duan, Yuanxing, et al.
Published: (2024)

UpFusion: Novel View Diffusion from Unposed Sparse View Observations
by: Kani, Bharath Raj Nagoor, et al.
Published: (2023)

The More You See in 2D, the More You Perceive in 3D
by: Han, Xinyang, et al.
Published: (2024)

PointCNN++: Performant Convolution on Native Points
by: Li, Lihan, et al.
Published: (2025)

Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
by: Chen, Kangjie, et al.
Published: (2025)

UniSem: Generalizable Semantic 3D Reconstruction from Sparse Unposed Images
by: Liao, Guibiao, et al.
Published: (2026)

GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering
by: Ye, Kai, et al.
Published: (2024)

Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
by: Zhou, Bo, et al.
Published: (2026)

RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing
by: Shao, Yiming, et al.
Published: (2026)

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
by: Ye, Botao, et al.
Published: (2024)

LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images
by: Liu, Yilong, et al.
Published: (2026)

SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images
by: Sheng, Yu, et al.
Published: (2025)

Pseudo-View Enhancement via Confidence Fusion for Unposed Sparse-View Reconstruction
by: Zhao, Beizhen, et al.
Published: (2026)

RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
by: Cheng, Chong, et al.
Published: (2025)

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

VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames
by: Li, Zhiqi, et al.
Published: (2025)

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
by: Chen, Xiaoxue, et al.
Published: (2025)

Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
by: Liu, Jiageng, et al.
Published: (2025)

Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding
by: Li, Jiaheng, et al.
Published: (2025)

FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
by: Shen, Qianfan, et al.
Published: (2026)

Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views
by: Zhang, Songchun, et al.
Published: (2024)

Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
by: Liu, Hongyuan, et al.
Published: (2026)

Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model
by: Huang, Yaxuan, et al.
Published: (2025)

Learning 3D-Aware GANs from Unposed Images with Template Feature Field
by: Chen, Xinya, et al.
Published: (2024)

LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images
by: He, Hao, et al.
Published: (2024)

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

SLGaussian: Fast Language Gaussian Splatting in Sparse Views
by: Chen, Kangjie, et al.
Published: (2024)

ZeroGS: Training 3D Gaussian Splatting from Unposed Images
by: Chen, Yu, et al.
Published: (2024)

Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views
by: Bao, Chong, et al.
Published: (2025)

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

Sparfels: Fast Reconstruction from Sparse Unposed Imagery
by: Jena, Shubhendu, et al.
Published: (2025)

From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images
by: Yu, Fei, et al.
Published: (2025)

YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos
by: Chen, Haoming, et al.
Published: (2025)

LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video
by: Quesado, Pedro, et al.
Published: (2026)

Large Spatial Model: End-to-end Unposed Images to Semantic 3D
by: Fan, Zhiwen, et al.
Published: (2024)

Less is More: Skim Transformer for Light Field Image Super-resolution
by: Hu, Zeke Zexi, et al.
Published: (2024)

DynSUP: Dynamic Gaussian Splatting from An Unposed Image Pair
by: Li, Weihang, et al.
Published: (2024)

Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images
by: Sun, Xiangyu, et al.
Published: (2025)

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