Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xiao, Yang, Xu, Guoan, Wu, Qiang, Jia, Wenjing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.03872
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913875067142144
author Xiao, Yang
Xu, Guoan
Wu, Qiang
Jia, Wenjing
author_facet Xiao, Yang
Xu, Guoan
Wu, Qiang
Jia, Wenjing
contents Reconstructing 3D scenes from sparse viewpoints is a long-standing challenge with wide applications. Recent advances in feed-forward 3D Gaussian sparse-view reconstruction methods provide an efficient solution for real-time novel view synthesis by leveraging geometric priors learned from large-scale multi-view datasets and computing 3D Gaussian centers via back-projection. Despite offering strong geometric cues, both feed-forward multi-view depth estimation and flow-depth joint estimation face key limitations: the former suffers from mislocation and artifact issues in low-texture or repetitive regions, while the latter is prone to local noise and global inconsistency due to unreliable matches when ground-truth flow supervision is unavailable. To overcome this, we propose JointSplat, a unified framework that leverages the complementarity between optical flow and depth via a novel probabilistic optimization mechanism. Specifically, this pixel-level mechanism scales the information fusion between depth and flow based on the matching probability of optical flow during training. Building upon the above mechanism, we further propose a novel multi-view depth-consistency loss to leverage the reliability of supervision while suppressing misleading gradients in uncertain areas. Evaluated on RealEstate10K and ACID, JointSplat consistently outperforms state-of-the-art (SOTA) methods, demonstrating the effectiveness and robustness of our proposed probabilistic joint flow-depth optimization approach for high-fidelity sparse-view 3D reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03872
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle JointSplat: Probabilistic Joint Flow-Depth Optimization for Sparse-View Gaussian Splatting
Xiao, Yang
Xu, Guoan
Wu, Qiang
Jia, Wenjing
Computer Vision and Pattern Recognition
Artificial Intelligence
Reconstructing 3D scenes from sparse viewpoints is a long-standing challenge with wide applications. Recent advances in feed-forward 3D Gaussian sparse-view reconstruction methods provide an efficient solution for real-time novel view synthesis by leveraging geometric priors learned from large-scale multi-view datasets and computing 3D Gaussian centers via back-projection. Despite offering strong geometric cues, both feed-forward multi-view depth estimation and flow-depth joint estimation face key limitations: the former suffers from mislocation and artifact issues in low-texture or repetitive regions, while the latter is prone to local noise and global inconsistency due to unreliable matches when ground-truth flow supervision is unavailable. To overcome this, we propose JointSplat, a unified framework that leverages the complementarity between optical flow and depth via a novel probabilistic optimization mechanism. Specifically, this pixel-level mechanism scales the information fusion between depth and flow based on the matching probability of optical flow during training. Building upon the above mechanism, we further propose a novel multi-view depth-consistency loss to leverage the reliability of supervision while suppressing misleading gradients in uncertain areas. Evaluated on RealEstate10K and ACID, JointSplat consistently outperforms state-of-the-art (SOTA) methods, demonstrating the effectiveness and robustness of our proposed probabilistic joint flow-depth optimization approach for high-fidelity sparse-view 3D reconstruction.
title JointSplat: Probabilistic Joint Flow-Depth Optimization for Sparse-View Gaussian Splatting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.03872