TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views
By: Hsiang-Hui Hung , Huu-Phu Do , Yung-Hui Li and more
Potential Business Impact:
Makes videos show any time of day.
We present TimeNeRF, a generalizable neural rendering approach for rendering novel views at arbitrary viewpoints and at arbitrary times, even with few input views. For real-world applications, it is expensive to collect multiple views and inefficient to re-optimize for unseen scenes. Moreover, as the digital realm, particularly the metaverse, strives for increasingly immersive experiences, the ability to model 3D environments that naturally transition between day and night becomes paramount. While current techniques based on Neural Radiance Fields (NeRF) have shown remarkable proficiency in synthesizing novel views, the exploration of NeRF's potential for temporal 3D scene modeling remains limited, with no dedicated datasets available for this purpose. To this end, our approach harnesses the strengths of multi-view stereo, neural radiance fields, and disentanglement strategies across diverse datasets. This equips our model with the capability for generalizability in a few-shot setting, allows us to construct an implicit content radiance field for scene representation, and further enables the building of neural radiance fields at any arbitrary time. Finally, we synthesize novel views of that time via volume rendering. Experiments show that TimeNeRF can render novel views in a few-shot setting without per-scene optimization. Most notably, it excels in creating realistic novel views that transition smoothly across different times, adeptly capturing intricate natural scene changes from dawn to dusk.
Similar Papers
QNeRF: Neural Radiance Fields on a Simulated Gate-Based Quantum Computer
CV and Pattern Recognition
Makes 3D pictures from photos using less computer power.
Neural Radiance Fields for the Real World: A Survey
CV and Pattern Recognition
Creates realistic 3D worlds from flat pictures.
VDNeRF: Vision-only Dynamic Neural Radiance Field for Urban Scenes
CV and Pattern Recognition
Makes robots see moving things and know where they are.