foliage
发表于 2025-3-30 11:07:41
http://reply.papertrans.cn/24/2342/234139/234139_51.png
Infuriate
发表于 2025-3-30 13:14:40
http://reply.papertrans.cn/24/2342/234139/234139_52.png
无脊椎
发表于 2025-3-30 17:50:03
http://reply.papertrans.cn/24/2342/234139/234139_53.png
Picks-Disease
发表于 2025-3-30 21:31:44
http://reply.papertrans.cn/24/2342/234139/234139_54.png
镀金
发表于 2025-3-31 04:21:45
Learning Inter-superpoint Affinity for Weakly Supervised 3D Instance Segmentationplying volume constraints of objects in clustering on the superpoint graph. Extensive experiments on the ScanNet-v2 and S3DIS datasets demonstrate that our method achieves state-of-the-art performance in the weakly supervised point cloud instance segmentation task, and even outperforms some fully su
巨硕
发表于 2025-3-31 06:12:34
http://reply.papertrans.cn/24/2342/234139/234139_56.png
相互影响
发表于 2025-3-31 12:52:26
SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesisd by a hypernetwork. As the parameters are conditioned on the image-encoded latent codes, SymmNeRF is thus scene-independent and can generalize to new scenes. Experiments on synthetic and real-world datasets show that SymmNeRF synthesizes novel views with more details regardless of the pose transfor
Oafishness
发表于 2025-3-31 15:10:37
Meta-Det3D: Learn to Learn Few-Shot 3D Object Detectionmples to characterize the task information, one for each distinct object class. Each re-weighting vector performs channel-wise attention to the candidate features to re-calibrate the query object features, adapting them to detect objects of the same classes. Finally, the adapted features are fed int
RAFF
发表于 2025-3-31 20:25:51
http://reply.papertrans.cn/24/2342/234139/234139_59.png