Views
No views yet
mvs package's live meshing pipeline.depth_model_dot.onnx — opset 17, batch dynamic (1..N): current image
Bx3x384x512, 7 source views, fp32 I/O with the fp16-autocast precision split baked into
the graph (TensorRT 11 strongly-typed builds consume it directly).cur_image_b3hw, src_image_bm3hw, src_K_bm44 (matching scale s1),
cur_invK_b44 (s1), src_cam_T_world_bm44, cur_world_T_cam_b44.depth_pred_s0_b1hw (Bx1x192x256 metric depth), lowest_cost_bhw.tools/export_trt.py (fp16 autocast trace, dot_product checkpoint).
Weights derive from Niantic's SimpleRecon (CC BY-NC-SA 4.0); non-commercial.