Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images
WaveDN: A Wavelet-based Training-free Zero-shot Enhancement for Vision-Language Models
J Li, M Yang, Y Tian, L Zhang, Y Lu, J Liu… - Proceedings of the 32nd …, 2024 - dl.acm.org
Vision-Language Models (VLMs) built on contrastive learning, such as CLIP, demonstrate
great transferability and excel in downstream tasks like zero-shot classification and retrieval …
great transferability and excel in downstream tasks like zero-shot classification and retrieval …
TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction
Dynamic scene reconstruction is a long-term challenge in 3D vision. Recent methods extend
3D Gaussian Splatting to dynamic scenes via additional deformation fields and apply explicit …
3D Gaussian Splatting to dynamic scenes via additional deformation fields and apply explicit …
DaRePlane: Direction-aware Representations for Dynamic Scene Reconstruction
Numerous recent approaches to modeling and re-rendering dynamic scenes leverage plane-
based explicit representations, addressing slow training times associated with models like …
based explicit representations, addressing slow training times associated with models like …