Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
Multi-view 3D reconstruction remains a core challenge in computer vision. Recent methods, such as DUST3R and its successors, directly regress pointmaps from image pairs without relying on known scene geometry or camera parameters. However, the performance of these models is constrained by the diversity and scale of available training data. In this work, we introduce Puzzles, a data augmentation strategy that synthesizes an unbounded volume of high-quality posed video-depth data from a single image or video clip. By simulating diverse camera trajectories and realistic scene geometry through targeted image transformations, Puzzles significantly enhances data variety. Extensive experiments show that integrating Puzzles into existing video-based 3D reconstruction pipelines consistently boosts performance without modifying the underlying network architecture. Notably, models trained on only ten percent of the original data augmented with Puzzles still achieve accuracy comparable to those trained on the full dataset. Code is available at https://jiahao-ma.github.io/puzzles/.
Jiahao Ma、Lei Wang、Miaomiao liu、David Ahmedt-Aristizabal、Chuong Nguyen
计算技术、计算机技术
Jiahao Ma,Lei Wang,Miaomiao liu,David Ahmedt-Aristizabal,Chuong Nguyen.Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction[EB/OL].(2025-06-30)[2025-07-16].https://arxiv.org/abs/2506.23863.点此复制
评论