Surf3R: Rapid Surface Reconstruction from Sparse RGB Views in Seconds
This addresses the practical deployment bottleneck for 3D reconstruction in applications requiring rapid processing, though it appears incremental as it builds on existing multi-view approaches.
The paper tackles the problem of slow and complex multi-view 3D reconstruction by introducing Surf3R, an end-to-end feedforward method that reconstructs 3D surfaces from sparse RGB views without camera pose estimation, completing scenes in under 10 seconds while achieving state-of-the-art performance on multiple metrics.
Current multi-view 3D reconstruction methods rely on accurate camera calibration and pose estimation, requiring complex and time-intensive pre-processing that hinders their practical deployment. To address this challenge, we introduce Surf3R, an end-to-end feedforward approach that reconstructs 3D surfaces from sparse views without estimating camera poses and completes an entire scene in under 10 seconds. Our method employs a multi-branch and multi-view decoding architecture in which multiple reference views jointly guide the reconstruction process. Through the proposed branch-wise processing, cross-view attention, and inter-branch fusion, the model effectively captures complementary geometric cues without requiring camera calibration. Moreover, we introduce a D-Normal regularizer based on an explicit 3D Gaussian representation for surface reconstruction. It couples surface normals with other geometric parameters to jointly optimize the 3D geometry, significantly improving 3D consistency and surface detail accuracy. Experimental results demonstrate that Surf3R achieves state-of-the-art performance on multiple surface reconstruction metrics on ScanNet++ and Replica datasets, exhibiting excellent generalization and efficiency.