issues
search
junyuan-fang
/
Vision-Language-on-3D-Scene-Understanding
MIT License
1
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Clip pointcloud to voxel with color
#19
junyuan-fang
closed
4 months ago
0
Clip pointcloud to voxel with color
#18
junyuan-fang
closed
4 months ago
0
readme
#17
junyuan-fang
closed
5 months ago
0
Clip
#16
junyuan-fang
closed
11 months ago
0
Download CLIP and get familiar with it
#15
junyuan-fang
opened
11 months ago
0
Create a repo for "CLIP-based 2D to 3D inflation for reffering pointcloud reasoning and segmentation"
#14
junyuan-fang
opened
11 months ago
0
Then combine the image encoder with the text encoder, check the model out, if it gives you something you wanted
#13
junyuan-fang
opened
11 months ago
0
Do not need to be segmentation, can try out the clasification first
#12
junyuan-fang
opened
11 months ago
0
test the inflated model with the 3d point input, check the output, if it is reasonable.
#11
junyuan-fang
opened
11 months ago
0
Test vision-transformer's inflation on the selected dataset
#10
junyuan-fang
opened
11 months ago
0
Test Image2point inflation on the selected dataset
#9
junyuan-fang
opened
11 months ago
0
How to minimize time complexity and space complexity. Data processing try to get the linear complexity
#8
junyuan-fang
opened
11 months ago
0
Collect5 papers which are related to “3D text scene understanding” by using CLIP or other models.
#7
junyuan-fang
opened
1 year ago
1
Multiview geometry
#6
junyuan-fang
opened
1 year ago
2
How to Train Really Large Models on Many GPUs?
#5
junyuan-fang
opened
1 year ago
0
Deep learning D
#4
junyuan-fang
opened
1 year ago
1
Papers to be read
#3
junyuan-fang
opened
1 year ago
1
Triton server
#2
junyuan-fang
opened
1 year ago
1
Viewing(not important)
#1
junyuan-fang
opened
1 year ago
1