TY - GEN
T1 - TimeNeRF
T2 - 32nd ACM International Conference on Multimedia, MM 2024
AU - Hung, Hsiang Hui
AU - Do, Huu Phu
AU - Li, Yung Hui
AU - Huang, Ching Chun
N1 - Publisher Copyright:
© 2024 ACM.
PY - 2024/10/28
Y1 - 2024/10/28
N2 - 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.
AB - 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.
KW - neural radiance field from sparse inputs
KW - time translation
UR - http://www.scopus.com/inward/record.url?scp=85209821850&partnerID=8YFLogxK
U2 - 10.1145/3664647.3681337
DO - 10.1145/3664647.3681337
M3 - Conference contribution
AN - SCOPUS:85209821850
T3 - MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia
SP - 253
EP - 262
BT - MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia
PB - Association for Computing Machinery, Inc
Y2 - 28 October 2024 through 1 November 2024
ER -