Sparse-View 3D Reconstruction: Recent Advances and Open Challenges

TL;DR

This survey reviews recent advances in sparse-view 3D reconstruction, focusing on neural implicit models, explicit point-cloud methods, and hybrid approaches, highlighting challenges and future directions for real-time, unconstrained applications.

Contribution

It provides a unified perspective on geometry-based, neural implicit, and generative methods, analyzing their trade-offs and outlining open challenges in the field.

Findings

Neural implicit models improve reconstruction in sparse views.

Explicit point-cloud methods like 3D Gaussian Splatting enhance accuracy.

Hybrid models leveraging diffusion and foundation models address artifacts.

Abstract

Sparse-view 3D reconstruction is essential for applications in which dense image acquisition is impractical, such as robotics, augmented/virtual reality (AR/VR), and autonomous systems. In these settings, minimal image overlap prevents reliable correspondence matching, causing traditional methods, such as structure-from-motion (SfM) and multiview stereo (MVS), to fail. This survey reviews the latest advances in neural implicit models (e.g., NeRF and its regularized versions), explicit point-cloud-based approaches (e.g., 3D Gaussian Splatting), and hybrid frameworks that leverage priors from diffusion and vision foundation models (VFMs).We analyze how geometric regularization, explicit shape modeling, and generative inference are used to mitigate artifacts such as floaters and pose ambiguities in sparse-view settings. Comparative results on standard benchmarks reveal key trade-offs between the reconstruction accuracy, efficiency, and generalization. Unlike previous reviews, our survey provides a unified perspective on geometry-based, neural implicit, and generative (diffusion-based) methods. We highlight the persistent challenges in domain generalization and pose-free reconstruction and outline future directions for developing 3D-native generative priors and achieving real-time, unconstrained sparse-view reconstruction.