DEPTH_NEURAL often gives missing disparity for not so near objects

[katsunori-waragai]

Preliminary Checks

• [X] This issue is not a duplicate. Before opening a new issue, please search existing issues.
• [X] This issue is not a question, feature request, or anything other than a bug report directly related to this project.

Description

DEPTH_MODE.NEURAL is expected to calculate disparity based on deep learning. Therefore, I acquired disparity while changing the combination of the following parameters.

init_params.camera_resolution
init_params.depth_mode

• As a result, I realized that the disparity of objects around 60cm and nearer may not be calculated when init_params.depth_mode = sl.DEPTH_MODE.NEURAL.

Steps to Reproduce

1. Prepare a script to save to save disparity data and depth_image using sl.DEPTH_MODE.ULTRA and using

        zed.retrieve_measure(disparity, sl.MEASURE.DISPARITY)
        disparity_img = disparity.get_data()
        zed.retrieve_image(depth_image, sl.VIEW.DEPTH)
        depth_image_img = depth_image.get_data()

2. Check if the object around 60 cm gives proper disparity. The disparity is_finite().
3. Modified the script to use sl.DEPTH_MODE.NEURAL
4. Check if the object around 60 cm gives proper disparity. The disparity is_finite().

Expected Result

disparity of the object at 60 cm should return finite disparity.

Actual Result

disparity of the object at 60 cm is isneginf.

It doesn't happen all the time, but it happens quite often.

ZED Camera model

ZED2i

Environment

OS: Ubuntu20 
CPU: ARM
GPU: Nvidia Jetson AGX Orin
ZED SDK version: 4.0.8

Anything else?

No response