Boxin Shi
Peking University, China
Event-based Photometric Imaging
A workshop at ACCV 2026, the 18th Asian Conference on Computer Vision, held in conjunction with the International Workshop on Image Sensors and Imaging Systems (IWISS) 2026 — bringing the Asia-Pacific image-sensor community and the computer-vision community into the same room.
Overview
Most computer-vision venues treat the image sensor as a fixed, conventional RGB camera. But a new generation of image sensors is rapidly reshaping what can be measured and, in turn, what vision algorithms can achieve.
This workshop focuses on the co-design of unconventional image sensors and the computer-vision and computational-imaging methods they enable. Its central premise is bidirectional: novel sensors give rise to novel CV/CI methods, and the demands of CV/CI in turn drive new sensor designs. Unusually for a computer-vision venue, sensor-hardware researchers are part of the organizing team, so the program reaches down to the device level rather than treating sensing as a fixed front end.
The workshop is the first of its kind at ACCV, and is held in conjunction with IWISS 2026, the biennial International Workshop on Image Sensors and Imaging Systems. Co-locating the two events connects an established sensor-side international community — much of the world's image-sensor industry sits in the Asia-Pacific region — with the computer-vision community.
Not a single sensor type: SPAD/single-photon, event/neuromorphic, time-of-flight and LiDAR, multispectral/SWIR/thermal, and in-sensor computing devices.
Image-sensor researchers organize and speak, so the program covers sensor design and fabrication — not only the algorithms that consume sensor data.
Both directions are on the table: new sensors enabling new CV/CI, and CV/CI requirements driving the next generation of sensors.
Scope
We welcome contributions across the full path from photons to inference, including but not limited to:
Program
Eleven invited talks bring the two communities into the same room, with speakers from computer vision and computational imaging alongside image-sensor and device researchers from academia and industry. Each invited talk is 25 minutes including Q&A. Talk titles marked tentative will be updated as they are confirmed; abstracts and speaker biographies will be posted as they are received.
Boxin Shi
Peking University, China
Event-based Photometric Imaging
Seung Ah Lee
Seoul National University, Korea
Design and Implementation of Task-Specific Lensless Cameras (tentative)
Kenichiro Tanaka
Ritsumeikan University, Japan
Thermal and Transient Imaging for Scene Understanding (tentative)
Kaushik Mitra
Indian Institute of Technology Madras, India
Computational Imaging with Single-Photon Cameras (tentative)
Seong-Jin Kim
Sogang University, Korea
A Fully Reconfigurable Hybrid SPAD Vision Sensor Featuring Time-Coded Dual Exposures
Liyuan Liu
Chinese Academy of Sciences, China
SPAD Vision Chips with Near-Sensor Spiking Neural Network Processing
Masahide Goto, Shigeyuki Imura and Hiroto Sato
Toyohashi University of Technology, Japan (Goto); NHK Science & Technology Research Laboratories, Japan (Imura, Sato)
3D Integrated Image Sensors and Flexible Image Sensors by Using SOI Technology
Chih-Cheng Hsieh
National Tsing Hua University, Taiwan
Processing-in-Sensor: From Imaging to Intelligence
Shunsuke Okura
Ritsumeikan University, Japan
Securing Vision at the Sensor: PUFs and Adversarial Example Defense
Youngcheol Chae
Yonsei University, Korea
Title to be announced
Sanggwong Lee
Samsung Electronics, Korea
A 1.494-µm-Pixel CMOS Image Sensor with Cluster-Level ADC and Motion Compensation for Global-Shutter-Equivalent Imaging in Mobile Applications
14 December 2026 · Room 1007
A full-day, in-person program of eleven invited talks and a poster session, from 9:00 to 17:15. Posters are on display throughout the day, with a dedicated 90-minute poster session in the afternoon. Minor changes may still be made; the final program will be confirmed in November 2026.
| Time | Program item |
|---|---|
| 09:00 – 09:10 | Opening remarks |
| 09:10 – 10:25 | Session 1 |
| 09:10 – 09:35 | Event-based Photometric ImagingBoxin Shi (Peking University, China) |
| 09:35 – 10:00 | A Fully Reconfigurable Hybrid SPAD Vision Sensor Featuring Time-Coded Dual ExposuresSeong-Jin Kim (Sogang University, Korea) |
| 10:00 – 10:25 | SPAD Vision Chips with Near-Sensor Spiking Neural Network ProcessingLiyuan Liu (Chinese Academy of Sciences, China) |
| 10:25 – 10:50 | Coffee break |
| 10:50 – 12:05 | Session 2 |
| 10:50 – 11:15 | Design and Implementation of Task-Specific Lensless Cameras (tentative)Seung Ah Lee (Seoul National University, Korea) |
| 11:15 – 11:40 | 3D Integrated Image Sensors and Flexible Image Sensors by Using SOI TechnologyMasahide Goto (Toyohashi University of Technology, Japan), Shigeyuki Imura and Hiroto Sato (NHK Science & Technology Research Laboratories, Japan) |
| 11:40 – 12:05 | Processing-in-Sensor: From Imaging to IntelligenceChih-Cheng Hsieh (National Tsing Hua University, Taiwan) |
| 12:05 – 13:30 | Lunch |
| 13:30 – 14:20 | Session 3 |
| 13:30 – 13:55 | Thermal and Transient Imaging for Scene Understanding (tentative)Kenichiro Tanaka (Ritsumeikan University, Japan) |
| 13:55 – 14:20 | Securing Vision at the Sensor: PUFs and Adversarial Example DefenseShunsuke Okura (Ritsumeikan University, Japan) |
| 14:20 – 15:50 | Poster session (with coffee break) |
| 15:50 – 17:05 | Session 4 |
| 15:50 – 16:15 | Computational Imaging with Single-Photon Cameras (tentative)Kaushik Mitra (Indian Institute of Technology Madras, India) |
| 16:15 – 16:40 | Title to be announcedYoungcheol Chae (Yonsei University, Korea) |
| 16:40 – 17:05 | A 1.494-µm-Pixel CMOS Image Sensor with Cluster-Level ADC and Motion Compensation for Global-Shutter-Equivalent Imaging in Mobile ApplicationsSanggwong Lee (Samsung Electronics, Korea) |
| 17:05 – 17:15 | Closing remarks |
Participation
We invite one-page abstracts for a non-archival poster session. The session is designed to be easy to join: there is no full-paper review, and previously published work is welcome.
The poster session is the main opportunity for students and early-career researchers to present at the workshop, and we particularly encourage submissions from groups working on new sensing modalities, sensor–algorithm co-design, and applications of unconventional cameras.
| Poster abstract deadline (extended) | 8 November 2026, 23:59 AoE |
| Notification to authors | 15 November 2026 |
| Final program announced | 15 November 2026 |
| Workshop | 14 December 2026 |
Please submit your one-page abstract (PDF) through the submission form by the deadline above (23:59 AoE). The form asks for the title, authors, affiliations, and the presenting author; the title and author names are shown on this website exactly as entered. You can edit your submission until the deadline.
The form requires signing in with a Google account. If you cannot access Google services, please email your PDF to smv2026@googlegroups.com with the subject “[SMV 2026 Poster] Your title”.
At least one author of each accepted abstract must present the poster in person on 14 December 2026, which requires registration for ACCV 2026.
Attending ACCV 2026? Authors of accepted ACCV 2026 papers on computational imaging, unconventional sensors, and related topics are warmly invited to present a poster here as well.
People
Professor, Research Institute of Electronics, Shizuoka University, Japan
Works on CMOS image sensor development for focal-plane time-compressive time-of-flight ranging based on multi-tap pixels, and on applications of new CMOS image sensors such as FLIM, DOT, and compressive video. He organizes the biennial International Workshop on Image Sensors and Imaging Systems (IWISS).
Assistant Professor, Institute of Systems and Information Engineering, University of Tsukuba, Japan
Works on computational imaging, computational photography, event-based vision, and computer graphics, bridging physics-based imaging and learning-based vision. His work has appeared at major computer-vision venues.
All enquiries about the workshop — the programme, the poster session, or participation — reach both organizers at smv2026@googlegroups.com.
Logistics
The workshop takes place on Monday, 14 December 2026 at the Osaka International Convention Center (Grand Cube Osaka), the venue of ACCV 2026. The centre is in Nakanoshima, Kita-ku, Osaka — a riverside district known for its art museums — about 10 minutes by taxi from Umeda, with a free shuttle bus from JR Osaka Station and a direct connection to Nakanoshima Station (exit 2) on the Keihan Nakanoshima line.
Attendance requires ACCV 2026 registration. Registration, travel, and accommodation are handled by the main conference; please see the ACCV 2026 website for details.
ACCV 2026 runs from 14 to 18 December 2026, with workshops and tutorials on 14–15 December and the main conference on 16–18 December.