JVal123

Registering depth information into RGB image

1

Hello! I've recently updated the hl2ss version from 1.012.0 to 1.025.0. Currently, I'm using the sample_integrator_pv.py script, which performs RGBD integration using Open3D. I've modified the script, simply to save...

OCRBenchV2

1

Hi! I did the benchmark of Pixtral-12B on OCRBench and noticed that it corresponds to the first version of this benchmark. Is OCRBenchv2 available?

Hi! I find that running the FOPA model is very time consuming (around 1 minute and 30 seconds for 10 image pairs). Is this to be expected?

Would it be possible to add the HuggingFace compatible version of Pixtral-12B? This is the one: mistral-community/pixtral-12b

Finetuned LLaVA Model output

4

Hi, I finetuned the LLaVA-v1.5-13B model and managed to benchmark it on a custom dataset. I noticed, however, that when benchmarking the finetuned version on that dataset, I didn't get...