Motion- and Gravity-Aware Feedforward 3D Reconstruction
arXiv:2610.22177v1 Announce Type: cross Abstract: Feed-forward transformer models have recently achieved strong performance in multi-view 3D reconstruction, but they still rely primarily on appearance-based attention and often struggle in dynamic scenes with weak geometric cues. In this work, we introduce a motion- and gravity-aware framework under the Learning Using Privileged Information (LUPI) paradigm. During training, residual optical flow and gravity direction are provided as privileged s…