Question about camera pose in groundtruth_handeye.txt about instant-dexnerf HOT 9 CLOSED

@JiayingGaoo you dont need to convert your poses to quaternions. You can directly use your transform.json. Make sure, that your poses are in opencv(=colmap) format.

from instant-dexnerf.

Hi @melhashash

Quaternions in groundtruth_handeye.txt follow the format (x, y, z, w), make sure that you use this convention. Let me know, if it solves the problem

If you have poses in colmap format, you can directly use them! You don't need to transform them in quaternions

from instant-dexnerf.

Hi,

I have a question about the convention used in groundtruth_handeye.txt. How to generate it given the pose in COLMAP format?

I tried the following code to generate groundtruth_handeye.txt and then use it with instrinsics.txt to generated the json file using ours2nerf.py but the generated camera poses are incorrect, as shown below (they should be 360)

This code reads images.txt file in COLMAP format

	for line in f:
		line = line.strip()
		if line[0] == "#":
			continue
		i = i + 1
		if i < SKIP_EARLY*2:
			continue
		if  i % 2 == 1:
			elems=line.split(" ") # 1-4 is quat, 5-7 is trans, 9ff is filename (9, if filename contains no spaces)
			image_rel = os.path.relpath(IMAGE_FOLDER)
			name = str(f"./{image_rel}/{'_'.join(elems[9:])}")	
			image_id = int(elems[0])
			qvec = np.array(tuple(map(float, elems[1:5])))
			tvec = np.array(tuple(map(float, elems[5:8])))
			R = qvec2rotmat(qvec)
			t = tvec.reshape([3,1])
			m = np.concatenate([np.concatenate([R, t], 1), bottom], 0)
			c2w = np.linalg.inv(m)
			R = c2w[:3,:3]
			t = c2w[:3,3]
			q = rotm2quat(R)
			f_c2w_pose_file.write(f"{counter} {q[0]} {q[1]} {q[2]} {q[3]} {t[0]} {t[1]} {t[2]}\n")
			counter = counter + 1

BTW, where is the definition of the function rotm2quat? I cannot find it

from instant-dexnerf.

@JiayingGaoo There is no rotm2quat function. It is @melhashash's code 😅

from instant-dexnerf.

Oh sorry. I just want to know how to generate groundtruth_handeye.txt by my own data, for now I have colmap_text and transform.json, then what to do? Thanks a lot

from instant-dexnerf.

BTW, where is the definition of the function rotm2quat? I cannot find it

I did not share the whole codes, only the loop to do conversion. Here it is:

def rotm2quat(m):
#q0 = qw
t = np.matrix.trace(m)
q = np.asarray([0.0, 0.0, 0.0, 0.0], dtype=np.float64)

if(t > 0):
    t = np.sqrt(t + 1)
    q[3] = 0.5 * t
    t = 0.5/t
    q[0] = (m[2,1] - m[1,2]) * t
    q[1] = (m[0,2] - m[2,0]) * t
    q[2] = (m[1,0] - m[0,1]) * t

else:
    i = 0
    if (m[1,1] > m[0,0]):
        i = 1
    if (m[2,2] > m[i,i]):
        i = 2
    j = (i+1)%3
    k = (j+1)%3

    t = np.sqrt(m[i,i] - m[j,j] - m[k,k] + 1)
    q[i] = 0.5 * t
    t = 0.5 / t
    q[3] = (m[k,j] - m[j,k]) * t
    q[j] = (m[j,i] + m[i,j]) * t
    q[k] = (m[k,i] + m[i,k]) * t

return q

from instant-dexnerf.

@salykovaa thanks!

As you mentioned, transform.json has the same format of colmap/opencv defined in the word coordinate system.

from instant-dexnerf.

transform.json

When I run scripts/main.py to generate depth images, it seems that I need to prepare three files: base.msgpack, intrinsics.txt and groundtruth_handeye.txt. Do you mean that groundtruth_handeye.txt is not necessary for my case (transform.json from colmap is enough)? Thanks a lot!

from instant-dexnerf.

transform.json

When I run scripts/main.py to generate depth images, it seems that I need to prepare three files: base.msgpack, intrinsics.txt and groundtruth_handeye.txt. Do you mean that groundtruth_handeye.txt is not necessary for my case (transform.json from colmap is enough)? Thanks a lot!

Yes, I think you only need to provide transform.json + images.

from instant-dexnerf.