Hi there, I wrote a small example based on BAL dataset, but I found it is extremely slow even on the smallest dataset(with the vectorize option off, CUDA out of memory reported if on), any good suggestion?

class BAGraph(nn.Module):

    def __init__(self, cameras, points, intrinsics):
        super().__init__()
        self.cameras = pp.Parameter(cameras)
        self.points = nn.Parameter(points)
        self.intrinsics = nn.Parameter(intrinsics)

    def forward(self, observations, camera_index, pt_index):
        pt_cam = self.cameras[camera_index, ...].Act(self.points[pt_index, ...])
        pt_image = -pt_cam[..., :2] / torch.unsqueeze(pt_cam[..., 2], 1)
        pt_norm = torch.linalg.vector_norm(pt_image, ord=2, dim=1)
        distortion_factors = 1 + self.intrinsics[camera_index, ..., 1] * pt_norm**2 + self.intrinsics[camera_index, ...,
                                                                                                      2] * pt_norm**4
        pt_pixel = torch.unsqueeze(self.intrinsics[camera_index, ..., 0], 1) * torch.unsqueeze(distortion_factors,
                                                                                               1) * pt_image
        error = pt_pixel - observations
        return error

Hi, we are currently implementing sparse tensors, which will solve this problem. @zitongzhan

BA is dependent on this issue: #207

Hi there, I wrote a small example based on BAL dataset, but I found it is extremely slow even on the smallest dataset(with the vectorize option off, CUDA out of memory reported if on), any good suggestion?

class BAGraph(nn.Module):

    def __init__(self, cameras, points, intrinsics):
        super().__init__()
        self.cameras = pp.Parameter(cameras)
        self.points = nn.Parameter(points)
        self.intrinsics = nn.Parameter(intrinsics)

    def forward(self, observations, camera_index, pt_index):
        pt_cam = self.cameras[camera_index, ...].Act(self.points[pt_index, ...])
        pt_image = -pt_cam[..., :2] / torch.unsqueeze(pt_cam[..., 2], 1)
        pt_norm = torch.linalg.vector_norm(pt_image, ord=2, dim=1)
        distortion_factors = 1 + self.intrinsics[camera_index, ..., 1] * pt_norm**2 + self.intrinsics[camera_index, ...,
                                                                                                      2] * pt_norm**4
        pt_pixel = torch.unsqueeze(self.intrinsics[camera_index, ..., 0], 1) * torch.unsqueeze(distortion_factors,
                                                                                               1) * pt_image
        error = pt_pixel - observations
        return error

Hello, you can try an unofficial pypose-native BAL colab example here. The smallest problem (problem-49-7776-pre) works fine on both CPU and GPU, and you can change the problem by using CLI parameters.

Any update on the official implementation for the differentiable BA?

Any update on the official implementation for the differentiable BA?

We are preparing for it and tuning its final APIs.

hi, any expected date for releasing this feature?