Hiral Joshi
@hiraljoshi
558 Following
334 Followers
1 reply
2 recasts
14 reactions
1 reply
2 recasts
28 reactions
5 replies
5 recasts
38 reactions
I met Nikelwa as she was returning from work, still wearing the white hair net from her job at the local fish factory, where young women are employed at low wages due to their lack of professional skills.
Despite the modesty of her factory attire, she radiated such beauty and grace that I was inspired to draw parallels to Thandiwe, the Zulu deity associated with love, beauty, and harmony. I added to the portrait a small scrap of luxurious fabric somebody gave me that day.
Interestingly, Nikelwa's name means "offering," and even at her young age, her life has already been marked by many sacrifices for her family, with, unfortunately, likely more to come.
'Portrait of Nikelwa'
2019 / South Africa
12 replies
24 recasts
50 reactions
1 reply
31 recasts
151 reactions
19 replies
20 recasts
39 reactions
7 replies
2 recasts
32 reactions
0 reply
3 recasts
32 reactions
My feeling is that it kinda has been for the past few years, and just doesn't seem to stop -- increasingly there is an on-going convergence of CV with General AI/ML - you saw it initially when CNNs blew every conventional computer vision methods (feature extraction, feature matching) with CNNs like AlexNet, Yolo, etc. Now with ViT vision transformers, and VLMs and the like. SAM (segment anything) is pretty amazing
That being said, edge perception stuff in the context of robotics, devices, AR/VR, and devices in general -- CV continues to be relevant. TinyML, perception models that are energy efficient and work on the edge GPU that it's meant to run on - prob a lot more work to do here, but if you look at companies like ST and TI, all they are making are MCUs that can run ML on it, so...
Also I am excited about 3D Gaussian splatting in the same way that I was excited aobut NeRFs, but 3D Gaussian splatting is a lot more efficient than NeRF - it can handle a lot more, order of magnitude more FPS. So that's cool 4 replies
22 recasts
114 reactions
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
1 reply
2 recasts
51 reactions
11 replies
23 recasts
61 reactions
61 replies
52 recasts
110 reactions
30 replies
26 recasts
56 reactions
6 replies
9 recasts
45 reactions
0 reply
3 recasts
58 reactions
105 replies
92 recasts
238 reactions
3 replies
6 recasts
67 reactions
4 replies
5 recasts
209 reactions
