Live intelligence

Latest AI updates

1 updates
Research Editor selected

EcoVGGT Uses Pinned Keys for Efficient Long-Video 3D Reconstruction

EcoVGGT is a training-free inference framework for feed-forward multi-view transformers that uses a Pinned Key Set of 31 evenly spread frames to make cross-frame attention cost constant per frame. It includes an online stream for updating pinned frames during recording and alignment modules that flag and reduce failures by fine-tuning six middle global blocks. On supplied evaluations, EcoVGGT with pi^3 matches pi^3’s success rate on 1,000-frame ScanNet videos at 13.8 times its speed, while refocused EcoVGGT with VGGT raises VGGT’s success rate from 70% to 82% at 8.5 times its speed on 500 frames. The method also reconstructs 4,000 frames on one GPU and streams 1,000 frames at 18.6 frames per second with the lowest online absolute trajectory error.

Why it matters: It gives readers a concrete way to run long-video 3D reconstruction more efficiently and streamably without full retraining.

VGGTpi^3feed-forward 3D reconstruction