Fuxin Li
LightNews LightNews
fuxinli.bsky.social
Fuxin Li
@fuxinli.bsky.social
48 followers 55 following 5 posts
Computer Vision, Explainable Deep Learning, Point Clouds, 3D Perception
Posts Replies Media Videos
Reposted by Fuxin Li
cvprconference.bsky.social
#CVPR2025 provided coaching for all orals. Do you think the talks were improved compared to last year?

* Better than last year
* About the same
* Worse than last year

Share your thoughts in the thread!
June 19, 2025 at 7:51 PM
Reposted by Fuxin Li
cvprconference.bsky.social
#AI-enhanced #robotics has become a growth area in computer vision, and the #CVPR2025 program reflects it. According to the technical program chairs, it’s an emerging trend for the conference. cvpr.thecvf.com/Conferences/...
A graphic for CVPR 2025 in Nashville, taking place June 11–15, 2025. The image features two program co-chairs: 1. Phillip Isola at MIT. His quote reads: “A lot of people in computer vision are now interested in robotics.” His photo is on the left. 2. Fuxin Li at Oregon State University. His quote reads: “We see more and more convergence between the two areas. There are also a lot more real robots in CVPR papers than a few years ago.” His photo is on the right. The background includes a stylised audio waveform and a guitar-shaped logo incorporating the word “Nashville.” Logos for CVF and IEEE Computer Society appear at the bottom left.
April 11, 2025 at 12:26 AM
fuxinli.bsky.social
We can usually only get partial observations of scenes, but getting complete object information could be helpful for many tasks in robotics and graphics. Our new ICLR 2025 paper extends point-based single object completion models to completing multiple objects in a scene, (1/3)🧵
February 11, 2025 at 6:59 AM