LL3DA

LL3DA copied to clipboard

Difference in results

1

  Why is the data so different, one is 0.a few, and the other is a few dozens

KongFulu

New object

9

Excuse me, I have a question, is the prediction of the box(ov-det) invalid for the objects other than the 17 objects defined? Because I found that objects will be filtered...

kuaileqipaoshui

Reproduction of QA Task Issues

4

Hello there! I'm interested in your work, but I'm having some differences when reproducing the results of the paper. So, I'd like to consult with you. 1. In the QA...

gaohan-cmd

Model use

3

Hello, can this large model be used directly and if it takes how long it takes to train

KongFulu

Dataset description

1

Do I need to download all the data of scannet? (1.3T)

yitianlian

Discrepancy Between Reproduced Model Results and Paper Findings

3

I attempted to reproduce the results of LL3DAl as described in the README. However, upon conducting experiments, I noticed a slight deviation in the results obtained compared to those reported...

heyucchen

Where can I get the dataset

1

Hi ,where can I get the 3d_llm data, and what 's the dimension of the scene, thank you ! 

Junxiao-Ma

Code release for models

7

Thanks for your nice work! But when I tried to run the code for training LL3DA, I found that the "models" module was missing. Is that correct? If so, could...

KairosXu

Qualitative result on scene description task

13

I've been conducting an evaluation test on unified_3dllm_scene_description dataset with the pretrained generalist ckpt [ll3da-opt-1.3b.pth](https://huggingface.co/CH3COOK/LL3DA-weight-release/blob/main/ll3da-opt-1.3b.pth). An example result for scene0612_00 is as below  ``` "scene0612_00": { "pred": [ "this...

jkstyle2

How to get grounding data?

1

Thanks for sharing the work. I notice that the model can output coordinates of the 3D bounding boxes throught numerical values. How to access this data related to 3D grounding...

Germany321