HI-SLAM2

HI-SLAM2 copied to clipboard

Save problem

7

Hello, may I ask if the pcd file can be generated in the end？

xl232lx

Hi, I have a similar problem to #3.

9

I increased CUDA_LAUNCH_BLOCKING=1, prepared the dataset as instructed and ran run_scannet.py, still a similar problem occurred, how can I solve it? 

lx6527562

Out of bounds error testing ScanNet scene0707_00

3

I random select scen0707_00 which has 784 images. And there is the error https://github.com/Willyzw/HI-SLAM2/blob/76c833c7d8ed474f0f3ba18056c1803e032a537f/hislam2/track_frontend.py#L68 ``` Exception has occurred: IndexError index 228 is out of bounds for dimension 0 with size...

7yzx

for scannet

2

(hislam2) gx@DESKTOP-UJ6NTN6:~/HISLAM2 (3)$ CUDA_LAUNCH_BLOCKING=1 python demo.py --imagedir data/scene0059_00/color --calib calib/scannet.txt --config config/scannet_config.yaml --output outputs/scene0059 \ > Processing keyframe 2 gs 0: 100%|█████████████████████████████████████████████████████████| 1024/1024 [00:29

galahies

Test on ScanNet++

1

Thank you very much for your excellent work. When I tested with ScanNet++ dataset, I used the scannet_config.yaml you provided. The data obtained is as shown in the figure below....

dmhedu

Hi @Willyzw 🤗 Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2411.17982. The paper page lets...

NielsRogge

Splatting for tracking

1

Hi @Willyzw , thank you so much for your excellent work, and for the open source code! In the paper, I noticed that Gaussian ''Splatting'' is primarily used for ''mapping'',...

ShunkaiZhou

The poor ATE on ScanNet

8

Hi @Willyzw , thank you so much for your excellent work!!! When I eval ScanNet scene0059_00, I get poor ATE result (61.61cm)  I'm sure that my dataset has been...

ShunkaiZhou

The poor performance of ScanNet

4

I download and test the performance of scannet_0000. The result is as follow:  Is something wrong about scannet_0000? Looking forward your reply.

kk6398

Hi, I have been testing HI-SLAM2 on the TUM dataset, and I observed a significant difference in reconstruction quality before and after offline optimization. I attached two [images:] Before offline...

Xiaosz-s