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:20240214T070249Z
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:Technical Papers\n\nZixi Shu, Ran Yi, Yuqi Meng, Yutong Wu, an
 d Lizhuang Ma (Shanghai Jiao Tong University)\n\nNeural Radiance Fields (N
 eRF) has demonstrated its ability to generate high-quality synthesized vie
 ws. Nonetheless, due to its slow inference speed, there is a need to explo
 re faster inference methods. In this paper, we propose RT-Octree, which us
 es batched regular tracking based on PlenOctree with neural denoising to a
 chieve better real-time performance. We achieve this by modifying the volu
 me rendering algorithm to regular tracking. We batch all samples for each 
 pixel in one single ray-voxel intersection process to further improve the 
 real-time performance. To reduce the variance caused by insufficient sampl
 es while ensuring real-time speed, we propose a lightweight neural network
  named GuidanceNet, which predicts the guidance map and weight maps utiliz
 ed for the subsequent multi-layer denoising module. We evaluate our method
  on both synthetic and real-world datasets, obtaining a speed of 100+ fram
 es per second (FPS) with a resolution of 1920 x 1080. Compared to PlenOctr
 ee, our method is 1.5 to 2 times faster in inference time and significantl
 y outperforms NeRF by several orders of magnitude. The experimental result
 s demonstrate the effectiveness of our approach in achieving real-time per
 formance while maintaining similar rendering quality.\n\nRegistration Cate
 gory: Full Access\n\nSession Chair: Yuchi Huo (Zhejiang University, Korea 
 Advanced Institute of Science and Technology)
URL:https://asia.siggraph.org/2023/full-program?id=papers_670&sess=sess154
END:VEVENT
END:VCALENDAR