Zeng Shuang
Zeng Shuang
Can the output get the actual size of the object?
video:  point_cloud.ply: Why the effect of video and point_cloud.ply varies greatly？
Does llamaGen still have the ability to generate text? Or is the ability greatly impaired?
Why is the error of the reconstructed point cloud from the measurement very large, the real value is 0.47m, but the point cloud measurement is 0.58m, a difference of 10cm
Do the obtained point clouds have real scale? For example, in real meters or centimeters
How do you solve the problem of the wrong number of image tokens generated by llm? For example, if the desired number of image tokens is 1024, will the model...
### 📚 The doc issue May I ask how to mark the key corners of the box? There is semantic ambiguity ### Suggest a potential alternative/fix _No response_
Can we get the true size of the object? Such as length, width and height
Could you please clarify if the camera pose orientation of Colmap is different from that of Dust3r? And how can we convert the orientation from Dust3r to that of Colmap?
When performing sparse reconstruction using the known camera intrinsic and extrinsic parameters, no point cloud was obtained at the end. There were no point clouds in the point triangulator stage...