PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis

Yu Zhu (Institute of automation, Chinese academy of science) · Qing Mao · Tianxin Huang (National University of Singapore) · Jinqiu Sun (Northwest Polytechnical University Xi'an) · Yanning Zhang (Northwestern Polytechnical University) · Gim Hee Lee (National University of Singapore)

3d visioncambridge landmarksdl3dv-10kfeature correspondencefeature matching selectorintermediate framesnavipairwise camera pose estimationpose estimation performancespose-conditioned novel view synthesisscannetself-consistency scoresota methodssynthesized resultsvideo interpolation

Pairwise camera pose estimation from sparsely overlapping image pairs remains a critical and unsolved challenge in 3D vision. Most existing methods struggle with image pairs that have small or no overlap. Recent approaches attempt to address this by synthesizing intermediate frames using video interpolation and selecting key frames via a self-consistency score. However, the generated frames are often blurry due to small overlap inputs, and the selection strategies are slow and not explicitly aligned with pose estimation. To solve these cases, we propose Hybrid Video Generation (HVG) to synthesize clearer intermediate frames by coupling a video interpolation model with a pose-conditioned novel view synthesis model, where we also propose a Feature Matching Selector (FMS) based on feature correspondence to select intermediate frames appropriate for pose estimation from the synthesized results. Extensive experiments on Cambridge Landmarks, ScanNet, DL3DV-10K, and NAVI demonstrate that, compared to existing SOTA methods, PoseCrafter can obviously enhance the pose estimation performances, especially on examples with small or no overlap.