Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding

1 code implementation • 15 Mar 2024 • Pengkun Liu, Yikai Wang, Fuchun Sun, Jiafang Li, Hang Xiao, Hongxiang Xue, Xinzhou Wang

As a result, with a single image CLIP embedding, Isotropic3D is capable of generating multi-view mutually consistent images and also a 3D model with more symmetrical and neat content, well-proportioned geometry, rich colored texture, and less distortion compared with existing image-to-3D methods while still preserving the similarity to the reference image to a large extent.

3D Generation Image to 3D +1

AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation

no code implementations • 6 Dec 2023 • Xinzhou Wang, Yikai Wang, Junliang Ye, Zhengyi Wang, Fuchun Sun, Pengkun Liu, Ling Wang, Kai Sun, Xintong Wang, Bin He

Extensive experiments demonstrate the capability of our method in generating high-flexibility text-guided 3D models from the monocular video, while also showing improved reconstruction performance over existing non-rigid reconstruction methods.

3D Generation Denoising +1

SNF: Filter Pruning via Searching the Proper Number of Filters

no code implementations • 14 Dec 2021 • Pengkun Liu, Yaru Yue, Yanjun Guo, Xingxiang Tao, Xiaoguang Zhou

Filter pruning with our method leads to the state-of-the-art (SOTA) accuracy on CIFAR-10 and achieves competitive performance on ImageNet ILSVRC-2012. SNF based on the ResNet-56 network achieves an increase of 0. 14% in Top-1 accuracy at 52. 94% FLOPs reduction on CIFAR-10.