BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163642Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T110500
DTEND;TZID=Australia/Melbourne:20231215T111500
UID:siggraphasia_SIGGRAPH Asia 2023_sess154_papers_670@linklings.com
SUMMARY:RT-Octree: Accelerate PlenOctree Rendering with Batched Regular Tr
 acking and Neural Denoising for Real-time Neural Radiance Fields
DESCRIPTION:Zixi Shu, Ran Yi, Yuqi Meng, Yutong Wu, and Lizhuang Ma (Shang
 hai Jiao Tong University)\n\nNeural Radiance Fields (NeRF) has demonstrate
 d its ability to generate high-quality synthesized views. Nonetheless, due
  to its slow inference speed, there is a need to explore faster inference 
 methods. In this paper, we propose RT-Octree, which uses batched regular t
 racking based on PlenOctree with neural denoising to achieve better real-t
 ime performance. We achieve this by modifying the volume rendering algorit
 hm to regular tracking. We batch all samples for each pixel in one single 
 ray-voxel intersection process to further improve the real-time performanc
 e. To reduce the variance caused by insufficient samples while ensuring re
 al-time speed, we propose a lightweight neural network named GuidanceNet, 
 which predicts the guidance map and weight maps utilized for the subsequen
 t multi-layer denoising module. We evaluate our method on both synthetic a
 nd real-world datasets, obtaining a speed of 100+ frames per second (FPS) 
 with a resolution of 1920 x 1080. Compared to PlenOctree, our method is 1.
 5 to 2 times faster in inference time and significantly outperforms NeRF b
 y several orders of magnitude. The experimental results demonstrate the ef
 fectiveness of our approach in achieving real-time performance while maint
 aining similar rendering quality.\n\nRegistration Category: Full Access\n\
 nSession Chair: Yuchi Huo (Zhejiang University, Korea Advanced Institute o
 f Science and Technology)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_670&sess=sess154
END:VEVENT
END:VCALENDAR