NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction
For researchers in 3D reconstruction and novel view synthesis, this work provides a method to mitigate pose drift in long sequences, improving scalability and robustness of feed-forward 3D Gaussian Splatting.
The paper addresses the problem of cumulative camera pose drift in long-sequence pose-free feed-forward 3D reconstruction, which degrades rendering quality. The proposed NoDrift3R framework, featuring a Raymap-Guided Coupling Module and Dual-Frequency Viewpoint Scheduling, achieves consistent improvements in rendering and pose estimation across in-domain and cross-domain datasets, with notably enhanced robustness on long sequences.
Pose-Free Feed-forward 3D Gaussian Splatting (3DGS) has recently emerged as a powerful paradigm for fast scene reconstruction. However, its performance degrades significantly in long image sequences due to cumulative camera pose estimation drift, which propagates errors into geometric modeling and severely limits rendering fidelity. In this work, we revisit the long-sequence bottleneck and identify pose drift as the primary factor restricting reconstruction quality. Furthermore, while SfM-based pseudo ground-truth poses introduce sensor noise, purely rendering-based supervision often leads to optimization instability and local minima due to the entangled optimization of geometry and pose. To address the challenges, we propose a synergistic pose-free framework that explicitly couples geometry and appearance via a Raymap-Guided Coupling Module (RGC). Concretely, we anchor Gaussian centers to raymap-induced geometry and jointly optimize RGB reconstruction, raymap consistency, and camera regularization under a unified objective, yielding a bidirectional feedback loop: stronger geometry improves rendering, and appearance supervision in turn refines geometry and pose. To further stabilize learning across wide temporal ranges, we introduce a Dual-Frequency Viewpoint Scheduling strategy that combines easy-to-hard interval expansion with replay of short-interval pairs. Extensive experiments across in-domain and cross-domain datasets show consistent gains in both rendering and pose estimation, with notably improved robustness on long sequences. Ablation studies validate our central insight: explicitly designed geometry-appearance synergy is the key to scalable and drift-robust pose-free feed-forward 3D reconstruction.