paper-with-me

홈 › Papers

Invertible Neural Warp for NeRF

2024-07-17 · Shin-Fang Chng, Ravi Garg, Hemanth Saratchandran, Simon Lucey

This paper tackles the simultaneous optimization of pose and Neural Radiance Fields (NeRF). Departing from the conventional practice of using explicit global representations for camera pose, we propose a novel overparameterized representation that models camera poses as learnable rigid warp functions. We establish that modeling the rigid warps must be tightly coupled with constraints and regularization imposed. Specifically, we highlight the critical importance of enforcing invertibility when learning rigid warp functions via neural network and propose the use of an Invertible Neural Network (INN) coupled with a geometry-informed constraint for this purpose. We present results on synthetic and real-world datasets, and demonstrate that our approach outperforms existing baselines in terms of pose estimation and high-fidelity reconstruction due to enhanced optimization convergence.

📄 PDF Abstract BibTeX arXiv:2407.12354

Code (0)

등록된 구현이 없습니다.

Tasks

NeRFPose Estimation

Similar Papers 제목 키워드 기반

Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fields

2023-07-24 · Shangzhan Zhang, Sida Peng, Yinji ShenTu, Qing Shuai 외

Recently, the editing of neural radiance fields (NeRFs) has gained considerable attention, but most prior works focus on static scenes while research on the appearance editing of dynamic scenes is relatively lacking. In …

NeRF

F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories

2023-03-28 · Peng Wang, YuAn Liu, Zhaoxi Chen, Lingjie Liu 외

This paper presents a novel grid-based NeRF called F2-NeRF (Fast-Free-NeRF) for novel view synthesis, which enables arbitrary input camera trajectories and only costs a few minutes for training. Existing fast grid-based …

NeRFNovel View Synthesis

F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories

2023-01-01 · CVPR 2023 1 · Peng Wang, YuAn Liu, Zhaoxi Chen, Lingjie Liu 외

This paper presents a novel grid-based NeRF called F^2-NeRF (Fast-Free-NeRF) for novel view synthesis, which enables arbitrary input camera trajectories and only costs a few minutes for training. Existing fast grid-b…

NeRFNovel View Synthesis

GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency

2023-01-26 · Min-Seop Kwak, Jiuhn Song, Seungryong Kim

We present a novel framework to regularize Neural Radiance Field (NeRF) in a few-shot setting with a geometry-aware consistency regularization. The proposed approach leverages a rendered depth map at unobserved viewpoint…

NeRF

Self-NeRF: A Self-Training Pipeline for Few-Shot Neural Radiance Fields

2023-03-10 · Jiayang Bai, Letian Huang, Wen Gong, Jie Guo 외

Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images. Despite its impressive performance, NeRF is plagued by its necessity for numerous calibrate…

NeRF