Segment Anything in 3D with Radiance Fields

1 code implementation • NeurIPS 2023 • Jiazhong Cen, Jiemin Fang, Zanwei Zhou, Chen Yang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian

The Segment Anything Model (SAM) emerges as a powerful vision foundation model to generate high-quality 2D segmentation results.

Inverse Rendering Segmentation

NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds

no code implementations • CVPR 2023 • Chen Yang, Peihao Li, Zanwei Zhou, Shanxin Yuan, Bingbing Liu, Xiaokang Yang, Weichao Qiu, Wei Shen

We present NeRFVS, a novel neural radiance fields (NeRF) based method to enable free navigation in a room.

A K-variate Time Series Is Worth K Words: Evolution of the Vanilla Transformer Architecture for Long-term Multivariate Time Series Forecasting

no code implementations • 6 Dec 2022 • Zanwei Zhou, RuiZhe Zhong, Chen Yang, Yan Wang, Xiaokang Yang, Wei Shen

In this study, we point out that the current tokenization strategy in MTSF Transformer architectures ignores the token uniformity inductive bias of Transformers.

Decoder Inductive Bias +2

DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation

no code implementations • 15 Mar 2022 • Yichao Yan, Zanwei Zhou, Zi Wang, Jingnan Gao, Xiaokang Yang

In this paper, we propose a novel unified framework based on neural radiance field (NeRF) to address this task.

Talking Head Generation Video Generation