Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
This addresses the problem of efficient and accurate 3D reconstruction from multiple images for computer vision applications, representing an incremental advancement over existing methods like DUSt3R.
The paper tackles the challenge of scalable multi-view 3D reconstruction by proposing Fast3R, a method that processes many images in parallel in one forward pass, achieving state-of-the-art performance with significant improvements in inference speed and reduced error accumulation.
Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a fundamentally pairwise approach, processing images in pairs and necessitating costly global alignment procedures to reconstruct from multiple views. In this work, we propose Fast 3D Reconstruction (Fast3R), a novel multi-view generalization to DUSt3R that achieves efficient and scalable 3D reconstruction by processing many views in parallel. Fast3R's Transformer-based architecture forwards N images in a single forward pass, bypassing the need for iterative alignment. Through extensive experiments on camera pose estimation and 3D reconstruction, Fast3R demonstrates state-of-the-art performance, with significant improvements in inference speed and reduced error accumulation. These results establish Fast3R as a robust alternative for multi-view applications, offering enhanced scalability without compromising reconstruction accuracy.