A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

no code implementations • 6 May 2024 • Kaiwen Jiang, Yang Fu, Mukund Varma T, Yash Belhe, Xiaolong Wang, Hao Su, Ravi Ramamoorthi

In this paper, we leverage the recent 3D Gaussian splatting method to develop a novel construct-and-optimize method for sparse view synthesis without camera poses.

Monocular Depth Estimation Novel View Synthesis

Equirectangular image construction method for standard CNNs for Semantic Segmentation

no code implementations • 13 Oct 2023 • Haoqian Chen, Jian Liu, Minghe Li, Kaiwen Jiang, Ziheng Xu, Rencheng Sun, Yi Sui

In addition, there are few publicly dataset of equirectangular images with labels, which presents a challenge for standard CNNs models to process equirectangular images effectively.

Data Augmentation Semantic Segmentation

NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields

1 code implementation • 15 Nov 2022 • Kaiwen Jiang, Shu-Yu Chen, Feng-Lin Liu, Hongbo Fu, Lin Gao

The geometry decoder aligns the original facial volume with the semantic mask volume.

Decoder Disentanglement

Individual vs. Joint Perception: a Pragmatic Model of Pointing as Communicative Smithian Helping

no code implementations • 3 Jun 2021 • Kaiwen Jiang, Stephanie Stacy, Chuyu Wei, Adelpha Chan, Federico Rossano, Yixin Zhu, Tao Gao

We add another agent as a guide who can only help by marking an observation already perceived by the hunter with a pointing or not, without providing new observations or offering any instrumental help.