V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints

Nathaniel Burgdorfer, Philippos Mordohai
2/14/2026

No official code found. Best implementation: nburgdorfer/V-FUSE (14 stars, last commit 2026-01-16).

Abstract

We introduce a learning-based depth map fusion framework that accepts a set of depth and confidence maps generated by a Multi-View Stereo (MVS) algorithm as input and improves them. This is accomplished by integrating volumetric visibility constraints that encode long-range surface relationships across different views into an end-to-end trainable architecture. We also introduce a depth search window estimation sub-network trained jointly with the larger fusion sub-network to reduce the depth hypothesis search space along each ray. Our method learns to model depth consensus and violations of visibility constraints directly from the data; effectively removing the necessity of fine-tuning fusion parameters. Extensive experiments on MVS datasets show substantial improvements in the accuracy of the output fused depth and confidence maps. Our code is available at https://github.com/nburgdorfer/V-FUSE

View on arXivView PDF

Code Implementations(1)

nburgdorfer/V-FUSECommunity100%

This is the official implementation of V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints.

140Shell, PythonAug 16, 20239 months ago

Similar Papers

PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

84% match1 repo1.0k2026

Depth-Guided Semi-Supervised Instance Segmentation

84% match2024

IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution

84% match2025

ConfidentSplat: Confidence-Weighted Depth Fusion for Accurate 3D Gaussian Splatting SLAM

83% match2025

EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objects

83% match2025

FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention

83% match2025

Cite this paper

@article{burgdorfer2026vfuse,
  title  = {V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints},
  author = {Nathaniel Burgdorfer and Philippos Mordohai},
  year   = {2026},
  eprint = {2308.08715},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2308.08715},
  journal = {ICCV 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.08715.svg)](https://codeofpaper.com/paper/2308.08715)

Discussion