ROMP icon indicating copy to clipboard operation
ROMP copied to clipboard

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

Results 205 ROMP issues
Sort by recently updated
recently updated
newest added

Shape损失的权重为6,而Pose的权重为80,这似乎导致模型在训练时并没有优化Shape(Shape损失很小且逐渐增加)?

Is there a way to get an output video that includes only the mesh instead of original+mesh?

Hey,on my cpu(i7 13700k),the ROMP only run about 3fps.Is it normal?It's my command: romp --mode=webcam --show --onnx

Hello, after a breifly test on BEV model, the result: BEV: 150ms ROMP: 54ms Does there any plan to provide a real-time version BEV model? Currently is too much more...

Hi @Arthur151. Several questions: - In the ROMP paper, I see that you have defined weighted loss. Looking into the `learnable_loss` function it seems that the total loss is just...

when i train BEV in colab enviroment, colab GPU resource is not avaliable. So i found that issue but i can't solution. this is my colab code. and dataset get...

作者您好,我想导出SMPL模型的22个点坐标,目前在用Blender导入.obj文件运行python脚本去获取,程序如下: import bpy import numpy as np mesh = bpy.context.object.data weights = np.ones(len(mesh.vertices)) matrices = np.array([bpy.context.object.matrix_world.inverted()] * len(mesh.vertices)) joint_indices = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9,...

@Arthur151 Hi, I have been looking into the Tables on comparisons across various models. There are several protocols. - Could you please help me understand the specific datasets used for...

Thank you for your excellent work. When trying to run the demo, I found that the real-time 3D model generated by webcam interaction produced a jitter. Still, there was no...

For a tracker.byte_tracker_3dcenter, I can see the tracking code is ` tracking_points = np.concatenate([(cams[:,[2,1]]+1)*image_scale, cam_trans[:,[2]]*depth_scale, cams[:,[0]]*image_scale/2],1) tracked_ids, results_inds = self.tracker.update(tracking_points, det_confs) ` the tracking_points is 4 float number. I want...