[cvpr] georef: geometric alignment across shape variation for category-level object pose refinement
Published 5 months ago • 25 plays • Length 4:55Download video MP4
Download video MP3
Similar videos
-
![[cvpr24 vision foundation models tutorial] image generation by zhengyuan yang](https://i.ytimg.com/vi/sOg2v3K9C2I/mqdefault.jpg)
58:32
[cvpr24 vision foundation models tutorial] image generation by zhengyuan yang
-
![[cvpr 2024] 3d human pose perception from egocentric stereo videos (conference video)](https://i.ytimg.com/vi/DOp2wocdSwo/mqdefault.jpg)
4:59
[cvpr 2024] 3d human pose perception from egocentric stereo videos (conference video)
-
![[cvpr 2024] decompose-and-compose: a compositional approach to mitigating spurious correlation](https://i.ytimg.com/vi/AtzYbLhBHCE/mqdefault.jpg)
5:16
[cvpr 2024] decompose-and-compose: a compositional approach to mitigating spurious correlation
-
5:40
introduction of mope-clip, accepted by cvpr 2024
-
![complementing event streams and rgb frames for hand mesh reconstruction [cvpr 2024]](https://i.ytimg.com/vi/cEVkQ10fWh0/mqdefault.jpg)
3:01
complementing event streams and rgb frames for hand mesh reconstruction [cvpr 2024]
-
5:05
cvpr 2024 - xfeat: accelerated features for lightweight image matching
-
5:23
video of cvpr 2024 paper draw step by step
-
9:55
hearing anything anywhere - cvpr 2024
-
![photo-slam for monocular, stereo, and rgb-d cameras [cvpr 2024]](https://i.ytimg.com/vi/hLal4fhvMrk/mqdefault.jpg)
5:01
photo-slam for monocular, stereo, and rgb-d cameras [cvpr 2024]
-
![[cvpr24 vision foundation models tutorial] multimodal agents by linjie li](https://i.ytimg.com/vi/h6D0sJltzI8/mqdefault.jpg)
42:53
[cvpr24 vision foundation models tutorial] multimodal agents by linjie li
-
6:18
gsnrerf: generalizable semantic neural radiance field (2024 cvpr)
-
![[cvpr 2024] scaling laws of synthetic images for model training ... for now](https://i.ytimg.com/vi/iiXQTR8dXcc/mqdefault.jpg)
4:54
[cvpr 2024] scaling laws of synthetic images for model training ... for now
-
2:21
cvpr 2024 recap and highlights
-
![[cvpr 2024 highlight] foundationpose: unified 6d pose estimation and tracking of novel objects](https://i.ytimg.com/vi/Ip_yWsGUF6c/mqdefault.jpg)
4:54
[cvpr 2024 highlight] foundationpose: unified 6d pose estimation and tracking of novel objects
-
![[cvpr 2024] language model assisted generation of images with coherence](https://i.ytimg.com/vi/XDMNEzH4-Ec/mqdefault.jpg)
8:44
[cvpr 2024] language model assisted generation of images with coherence
-
![[cvpr 2024] sportsslomo: a new benchmark and baselines for human-centric video frame interpolation](https://i.ytimg.com/vi/SkL-LOKksgk/mqdefault.jpg)
7:20
[cvpr 2024] sportsslomo: a new benchmark and baselines for human-centric video frame interpolation
-
![[cvpr 2024] at-edm: attention-driven training-free efficiency enhancement of diffusion models](https://i.ytimg.com/vi/ZmOdN4F_8Ew/mqdefault.jpg)
4:43
[cvpr 2024] at-edm: attention-driven training-free efficiency enhancement of diffusion models
-
5:02
cvpr 2024 amodal ground truth and completion in the wild