BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030655Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251217T165100
DTEND;TZID=Asia/Hong_Kong:20251217T170200
UID:siggraphasia_SIGGRAPH Asia 2025_sess144_papers_1890@linklings.com
SUMMARY:Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Deco
 mposing Two-Bounce Light
DESCRIPTION:Tzofi Klinghoffer and Siddharth Somasundaram (MIT Media Lab); 
 Xiaoyu Xiang, Yuchen Fan, and Christian Richardt (Meta); Akshat Dave and R
 amesh Raskar (MIT Media Lab); and Rakesh Ranjan (Meta)\n\n3D scene reconst
 ruction from a single measurement is challenging, especially in the presen
 ce of occluded regions and specular materials, such as mirrors. We address
  these challenges by leveraging single-photon lidars. These lidars estimat
 e depth from light that is emitted into the scene and reflected directly b
 ack to the sensor. However, they can also measure light that bounces multi
 ple times in the scene before reaching the sensor. This multi-bounce light
  contains additional information that can be used to recover dense depth, 
 occluded geometry, and material properties. Prior work with single-photon 
 lidar, however, has only demonstrated these use cases when a laser sequent
 ially illuminates one scene point at a time. We instead focus on the more 
 practical - and challenging - scenario of illuminating multiple scene poin
 ts simultaneously. The complexity of light transport due to the combined e
 ffects of multiplexed illumination, two-bounce light, shadows, and specula
 r reflections is challenging to invert analytically. Instead, we propose a
  data-driven method to invert light transport in single-photon lidar. To e
 nable this approach, we create the first large-scale simulated dataset of 
 ~100k lidar transients for indoor scenes. We use this dataset to learn a p
 rior on complex light transport, enabling measured two-bounce light to be 
 decomposed into the constituent contributions from each laser spot. Finall
 y, we experimentally demonstrate how this decomposed light can be used to 
 infer 3D geometry in scenes with occlusions and mirrors from a single meas
 urement.\n\nRegistration Category: Full Access, Full Access Supporter\n\nS
 ession Chair: Seung-Hwan Baek (POSTECH)\n\n
END:VEVENT
END:VCALENDAR