ximgproc: optimize Adaptive Manifold function for ARM64

[pratham-mcw]

Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

• I agree to contribute to the project under Apache 2 License.

• To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV

• The PR is proposed to the proper branch

• This PR introduces an ARM64-specific performance optimization in AdaptiveManifoldFilter::h_filter by applying loop unrolling.

• The optimization is guarded with #if defined(_M_ARM64) to ensure it only affects ARM64 builds.

• The optimization does not affect accuracy and maintains the same numerical behavior as the original scalar implementation.

Performance Improvements :

• The optimization significantly improves the performance of adaptive Manifold function on Windows ARM64 targets.
• The table below shows timing comparisons before and after the optimization:

[pratham-mcw]

Hi @asmorkalov, just following up on this PR. The loop unrolling in the h_filter function has shown significant performance improvements on Windows-ARM64 targets, while maintaining functional correctness across other architectures.
Please let me know if there are any additional changes or updates you’d like me to make.

[asmorkalov]

I do not see stable improvement on Linux ARM (GCC, Jetson Orin). SO let's merge as is without check extension.