LAB LOGA page on LabLog, a review site (not the lab's official page)
Heming Sun Lab
Machine-translated · View original
A lab that develops image and video compression technology, all the way down to the circuit level.
AboutAbout the lab
From algorithms to hardware.
The Heming Sun Lab studies image processing, neural networks, and the acceleration of related hardware.
The lab covers visual computing broadly, from learning algorithms to highly efficient hardware systems.
Its research themes include video compression, generative models, acceleration with FPGAs and ASICs, and large language models.
The lab aims to turn research ideas into highly efficient systems that actually work.
Key terms
- Neural network
- A computational mechanism modeled on the connections between neurons in the brain. It learns features from many examples
- Encoding
- Converting data into signals of a fixed format. For images and video, it refers to compression that reduces the amount of data
- FPGA
- An integrated circuit whose internal circuitry can be reconfigured after purchase. It allows dedicated circuits tailored to a purpose to be tested quickly
NewsLab news
Paper accepted at IEEE Transactions on Multimedia
Paper accepted in a video technology journal
Paper accepted at ICML 2026, an international machine learning conference
Paper accepted at ISCAS 2026, an international conference on circuits and systems
Paper accepted at ICASSP 2026, an international conference on signal processing
ResearchResearch themes
The lab explores visual computing, from learning algorithms to highly efficient hardware systems. It studies image and video compression end to end, from the design of neural networks to the implementation of FPGA and ASIC circuits.
*Illustrative imageLearned image compression
The lab studies methods that use neural networks to encode images with high efficiency.
Learned video compression
The lab encodes video by making use of motion information and an attention mechanism that selects important regions at the feature level.
*Illustrative imageImage coding for machines
Focusing on tasks in which machines recognize images, the lab works on compression that prioritizes semantic information.
*Illustrative imageImage compression on FPGAs
From the design of FPGA architectures to real-time demos that actually run, the lab makes learned image compression highly efficient.
MembersFaculty
The Heming Sun Lab consists of faculty members, a secretary, postdoctoral researchers, and doctoral, master's, and undergraduate students.As of 2026
- Associate ProfessorHeming Sun HemingPublications ↗
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Heming Sun Lab
Kenji Kise LabSchool of Computing, Department of Computer ScienceComputer systems, parallel processing, and FPGAs (architectu…
Shunsuke Ono LabSchool of Computing, Department of Computer ScienceSensing data analysis using image processing, signal process…
Yang Cao LabSchool of Computing, Department of Computer ScienceTrustworthy large language models and privacy-preserving dat…
Okazaki LabSchool of Computing, Department of Computer ScienceNatural language processing, machine learning (language anal…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Red-Square-sub-pixel-weirdness” librsvg2.40, Lommes / CC0 (cropped)
- Learned image compression: “JPEG compression Example” JJ Harrison, side-by-side comparison by Ibrahim.ID / CC BY-SA 3.0 (cropped)
- Image coding for machines: “Detected-with-YOLO--Schreibtisch-mit-Objekten” (MTheiler) / CC BY-SA 4.0 (cropped)
- Image compression on FPGAs: “TEI0001 Altera MAX 10 FPGA MAX1000 IoT Maker Board top view” Antti Lukats / CC0 (cropped)
- Related lab (吉瀬研究室): “Cray 1 IMG 9126” Rama / CC BY-SA 2.0 fr (cropped)
- Related lab (小野
（峻） 研究室): “Cable racks at grid computing center, Fermilab with blue lights” ENERGY.GOV / Public domain (cropped) - Related lab (曹研究室): “Cybersecurity” jaydeep_ / CC0 (cropped)
- Related lab (岡崎研究室): “Birthdaytagcloud” User:Killiondude / Public domain (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.