MoGe
MoGe copied to clipboard
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
Thank you for your greet work! 1. I would like to ask if **data-refinement** has plans to open source it, and when it will be open sourced. 2. I noticed...
Why is Moge's detail geometry so good? Does its detail geometry originate from the Affine-invariant point map or the Multi-scale local geometry loss? For example, in an autonomous driving scenario,...
moge v2,fine turning。We used our own dataset to fine-tune the model, which, together with the pre-trained model, performed depth estimation on the same image, yielding identical results. What went wrong?
不同的数据集深度数值的单位不同,有的数据集以米(m)为单位,有的数据集以毫米(mm)为单位,请问制作数据的过程中需要统一单位吗?
Outstanding work! I've created a workflow and custom nodes on ComfyUI that support both MoGe and MoGe2 models. https://github.com/zade23/ComfyUI-MoGe2  I hope this can help game developers and artists :)
I would like to fine-tune the current model on an autonomous driving dataset to obtain more accurate depth estimation. May I directly use the sparse LiDAR image as the depth...
The repo has MIT and Apache 2.0 licenses, but no clear mention of the provided model weights are of which license. Links in the repo point to the Huggingface where...
I found that the metric_scale prediction result has no corresponding supervision function. Doesn’t this lead to scale errors in the estimation?