GeoFusionLRM: Geometry-Aware Self-Correction for Consistent 3D Reconstruction
Preprint
Abstract
Single-image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry-aware self-correction framework that leverages the model's own normal and depth predictions to refine structural accuracy. Unlike prior approaches that rely solely on features extracted from the input image, GeoFusionLRM feeds back geometric cues through a dedicated transformer and fusion module, enabling the model to correct errors and enforce consistency with the conditioning image. This design improves the alignment between the reconstructed mesh and the input views without additional supervision or external signals. Extensive experiments demonstrate that GeoFusionLRM achieves sharper geometry, more consistent normals, and higher fidelity than state-of-the-art LRM baselines.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Progressive Learning of 3D Reconstruction Network From 2D GAN DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Fine Detailed Texture Learning for 3D Meshes With Generative ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Flexible Isosurface Extraction for Gradient-Based Mesh OptimizationACM Transactions on Graphics, 2023
- Shape and Viewpoint Without Keypoints2020