Peng Wang, Ziwei Liu, Yuan Liu, Christian Theobalt, Lingjie Liu, Wenping Wang, Taku Komura, Zhaoxi Chen
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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-based NeRF training frameworks, like Instant-NGP, Plenoxels, DVGO, or TensoRF, are mainly designed for bounded scenes and rely on space warping to handle unbounded scenes. Existing two widely-used space-warping methods are only designed for the forward-facing trajectory or the 360 • object-centric trajectory but cannot process arbitrary trajectories. In this paper, we delve deep into the mechanism of space warping to handle unbounded scenes. Based on our analysis, we further propose a novel space-warping method called perspective warping, which allows us to handle arbitrary trajectories in the grid-based NeRF framework. Extensive experiments demonstrate that F 2 -NeRF is able to use the same perspective warping to render high-quality images on two standard datasets and a new free trajectory dataset collected by us. Project page: totoro97.github.io/ projects/ f2-nerf .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.15951")
get_code_for_paper("2303.15951")
have("2303.15951")
Connect an agent — have() is free.