3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces

Linyi Jin, Nilesh Kulkarni, David F. Fouhey
2/9/2026

No official code found. Best implementation: jinlinyi/3DFIRES (26 stars, MIT, last commit 2024-03-28).

Abstract

This paper introduces 3DFIRES, a novel system for scene-level 3D reconstruction from posed images. Designed to work with as few as one view, 3DFIRES reconstructs the complete geometry of unseen scenes, including hidden surfaces. With multiple view inputs, our method pro-duces full reconstruction within all camera frustums. A key feature of our approach is the fusion of multi-view information at the feature level, enabling the production of coherent and comprehensive 3D reconstruction. We train our system on non-watertight scans from large-scale real scene dataset. We show it matches the efficacy of single-view reconstruction methods with only one input and surpasses existing techniques in both quantitative and qualitative measures for sparse-view 3D reconstruction. Project page: https://jinlinyi.github.io/3DFIRES/

View on arXivView PDF

Code Implementations(1)

jinlinyi/3DFIRESCommunity64%
MIT

[CVPR 2024] 3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces

262Shell, PythonMar 6, 20242 years agoMIT
3d-scene-reconstructionocclusion

Similar Papers

GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction

88% match2025

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

86% match1 repo6062026

Generic Objects as Pose Probes for Few-shot View Synthesis

86% match1 repo52024

CSS: Overcoming Pose and Scene Challenges in Crowd-Sourced 3D Gaussian Splatting

85% match2024

PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction

85% match2024

FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency

85% match1 repo1152025

Cite this paper

@article{jin2026dfires,
  title  = {3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces},
  author = {Linyi Jin and Nilesh Kulkarni and David F. Fouhey},
  year   = {2026},
  eprint = {2403.08768},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2403.08768},
  journal = {CVPR 2024 2024}
}

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/2403.08768.svg)](https://codeofpaper.com/paper/2403.08768)

Discussion