CVPR 2026

6/3 (Wed) ～ 6/7 (Sun), 2026 at Colorado Convention Center, Colorado, US

The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) is the premier annual computer vision, and AI event. More than 9,000 professionals from 75 different countries participate, from academia and industry where they are hard at work in developing the next generation of computer vision and AI algorithms, experimental and commercial computer vision products and intelligent systems.

Sony is proud to be Platinum sponsor of CVPR 2026. We look forward to this year's exciting exhibition opportunities, featuring a variety of ways to connect with participants in person. Sony will exhibit and participate.

Contents: Sony's Technical Programs at CVPR 2026; Exhibition Booth; Follow us on LinkedIn!; Sony Women in Technology Award with Nature; Career Information

Sony's Technical Programs at CVPR 2026

Oral

PAVAS: Physics-Aware Video-to-Audio Synthesis

- Authors: Oh Hyun-Bin, Yuhta Takida (Sony AI), Toshimitsu Uesaka (Sony AI), Tae-Hyun Oh, Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time:
[Oral Session 3D] June 6th (Sat) 9:00 – 10:15 (MDT)
[Poster Session 3] June 6th (Sat) 11:45 - 13:45 (MDT)
- Place:
[Oral Session 3D] Mile High Ballroom 3A - 4A
[Poster Session 3] ExHall F 23

< Link >
- [CVPR/Oral] https://cvpr.thecvf.com/virtual/2026/oral/40364
- [CVPR/Poster] https://cvpr.thecvf.com/virtual/2026/poster/39327
- [Paper] https://arxiv.org/abs/2512.08282
- [GitHub] https://physics-aware-video-to-audio-synthesis.github.io/

Posters - Main Track

Highlight
B³-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta–Bernoulli Bayesian Updates

- Authors: Hiromichi Kamata (Sony Group Corporation), Samuel Arthur Munro (Pixomondo), Fuminori Homma (Sony Group Corporation)
- Date/Time: [Poster Session 4] June 6th (Sat) 16:45 - 18:45 (MDT)
- Place: ExHall A & F 507

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/38552
- [Paper] https://arxiv.org/abs/2602.17134
- [Github] https://sony.github.io/B3-Seg-project/

Highlight
Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision

- Authors: Zitang Sun (Sony Group Corporation), Masakazu Yoshimura (Sony Group Corporation), Junji Otsuka (Sony Group Corporation), Atsushi Irie (Sony Group Corporation), Takeshi Ohashi (Sony Group Corporation)
- Date/Time: [Poster Session 5] June 7th (Sun) 11:45 - 13:45 (MDT)
- Place: ExHall F 388

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/36353
- [Paper] https://arxiv.org/abs/2511.14197

Highlight
Dark3R: Learning Structure from Motion in the Dark

- Authors: Andrew Y. Guo, Anagh Malik, SaiKiran Tedla, Yutong Dai (Sony Corporation of America), Yiqian Qin, Zach Salehe, Benjamin Attal, Sotiris Nousias, Kiriakos N. Kutulakos, David B. Lindell
- Date/Time: [Poster Session 5] June 7th (Sun) 11:45 - 13:45 (MDT)
- Place: ExHall F 516

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/39382
- [Paper] https://arxiv.org/pdf/2603.05330

EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer

- Authors: Munish Monga (Sony Research India), Vishal Chudasama (Sony Research India), Pankaj Wasnik (Sony Research India), C.V. Jawahar
- Date/Time: [Poster Session 2] June 5th (Fri) 16:00 - 18:00 (MDT)
- Place: Exhall A & F 385

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/37800
- [Paper] https://arxiv.org/abs/2602.20985

Learning Compact 3D Representations from Feed-Forward Novel View Synthesis

- Authors: Honggyu An, Jaewoo Jung, Mungyeom Kim, Chaehyun Kim, Minkyeong Jeon, Jisang Han, Kazumi Fukuda (Sony AI), Takuya Narihira (Sony AI), Hyunah Ko, Junsu Kim, Sunghwan Hong, Yuki Mitsufuji (Sony AI), Seungryong Kim
- Date/Time: [Poster Session 1] June 5th (Fri) 10:45 - 12:45 (MDT)
- Place: ExHall A-F 35

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/37749
- [Paper] https://arxiv.org/abs/2512.04021

MeanFlow Transformers with Representation Autoencoders

- Authors: Zheyuan Hu, Chieh-Hsin Lai (Sony AI), Ge Wu, Yuki Mitsufuji (Sony AI/Sony Group Corporation), Stefano Ermon
- Date/Time: [Poster Session 4] June 6th (Sat) 16:45 - 18:45 (MDT)
- Place: ExHall A & F 398

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/39530
- [Paper] https://arxiv.org/abs/2511.13019

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation

- Authors: Onkar Susladkar, Tushar Prakash (Sony Research India), Adheesh Juvekar, Kiet A. Nguyen, Dong-Hwan Jang, Inderjit S Dhillon, Ismini Lourentzou
- Date/Time: [Poster Session 6] June 7th (Sun) 15:30 - 17:30 (MDT)
- Place: ExHall A 161

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/39433
- [Paper] https://arxiv.org/abs/2601.16210

RewardFlow: Generate Images by Optimizing What You Reward

- Authors: Onkar Susladkar, Dong-Hwan Jang, Tushar Prakash (Sony Research India), Adheesh Juvekar, Vedant Shah, Ayush Barik, Nabeel Bashir, Muntasir Wahed, Ritish Shrirao, Ismini Lourentzou
- Date/Time: [Poster Session 3] June 6th (Sat) 11:45 - 13:45 (MDT)
- Place: ExHall F 543

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/37655
- [GitHub] https://arxiv.org/abs/2604.08536

UniCompress: Token Compression for Unified Vision–Language Understanding and Generation

- Authors: Ziyao Wang, Chen Chen (Sony AI), Jingtao Li (Sony AI), Weiming Zhuang (Sony AI), Jiabo Huang (Sony AI), Ang Li, Lingjuan Lyu (Sony AI)
- Date/Time: [Poster Session 4] June 6th (Sat) 16:45 - 18:45 (MDT)
- Place: ExHall A & F 301

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/38630
- [Paper] https://arxiv.org/abs/2603.11320

VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations

- Authors: Maitreya Patel, Jingtao Li (Sony AI), Weiming Zhuang (Sony AI), Yezhou Yang, Lingjuan Lyu (Sony AI)
- Date/Time: [Poster Session 1] June 5th (Fri) 10:45 - 12:45 (MDT)
- Place: ExHall A-F 190

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/37635
- [GitHub] https://github.com/SonyResearch/VibeToken/

Asynchronous Temporal Modeling with Two-Agent Framework for Streaming Dense Video Captioning

- Authors: Yolo Yunlong Tang, Chao Huang, Susan Liang, Jing Bi, Yicheng Wang, Daiki Shimada (Sony Group Corporation), Chenliang Xu
- Date/Time: [Poster Session 1] June 5th (Fri) 10:45 - 12:45
- Place: ExHall A-F 258

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/39980

BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models

- Authors: Shengao Wang, Wenqi Wang, Zecheng Wang, Max Whitton, Michael Wakeham, Arjun Chandra, Joey Huang, Pengyue Zhu, Helen Chen, David Li, Jeffrey Li, Shawn Li, Andrew Zagula, Amy Zhao, Andrew Zhu, Sayaka Nakamura (Sony Group Corporation), Yuki Yamamoto (Sony Group Corporation), Jerry Jun Yokono (Sony Group Corporation), Aaron Mueller, Bryan A. Plummer, Kate Saenko, Venkatesh Saligrama, Boqing Gong
- Date/Time: [Poster Session 4] June 6th (Sat) 16:45 - 18:45 (MDT)
- Place: ExHall A & F 211

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/37763
- [Paper] https://arxiv.org/abs/2512.10932

Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

- Authors: Christian Simon (Sony Group Corporation), Masato Ishii (Sony AI), Wei-Yao Wang (Sony Group Corporation), Koichi Saito (Sony AI), Akio Hayakawa (Sony AI), Dongseok Shim (Sony Group Corporation), Zhi Zhong (Sony Group Corporation), Shuyang Cui (Sony Group Corporation), Takashi Shibuya (Sony AI), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: [Poster Session 3] June 6th (Sat) 11:45 - 13:45 (MDT)
- Place: ExHall F 149

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/38291
- [Paper] https://arxiv.org/abs/2602.20981

Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal

- Authors: Kazuma Ikeda, Ryosei Hara, Rokuto Nagata, Ozora Sako, Zihao Ding, Takahiro Kado (Sony Semiconductor Solutions), Ibuki Fujioka (Sony Semiconductor Solutions), Taro Beppu (Sony Semiconductor Solutions), Mariko Isogawa, Kentaro Yoshioka
- Date/Time: [Poster Session 3] June 6th (Sat) 11:45 - 13:45 (MDT)
- Place: ExHall F 271

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/37610
- [Paper] https://arxiv.org/abs/2603.28224

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation

- Authors: Xinshun Wang, Peiming Li, Ziyi Wang, Zhongbin Fang, Zhichao Deng, Songtao Wu (Sony China Limited), Xiangtai Li, Mengyuan Liu
- Date/Time: [Poster Session 6] June 7th (Sun) 15:30 - 17:30 (MDT)
- Place: ExHall A 201

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/36903
- [Paper] https://arxiv.org/abs/2602.02401

Posters - Findings Track

Face Time Traveller: Travel Through Ages Without Losing Identity

- Authors: Purbayan Kar (Sony Research India), Ayush Ghadiya (Sony Research India), Vishal Chudasama (Sony Research India), Pankaj Wasnik (Sony Research India), C.V. Jawahar
- Date/Time: June 7th (Sun) 07:30 - 9:00 (MDT)
- Place: ExHall A 212

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/41364
- [Paper] https://arxiv.org/abs/2602.22819

UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models

- Authors: Yimu Wang, Weiming Zhuang (Sony AI), Chen Chen (Sony AI), Jiabo Huang (Sony AI), Jingtao Li (Sony AI), Lingjuan Lyu (Sony AI)
- Date/Time: June 5th (Fri) 07:00 - 8:30 (MDT>
- Place: ExHall A 282

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/poster/40797
- [Paper] https://arxiv.org/abs/2508.19498

Tutorial

The Principles of Diffusion Models: Real-Time Continuous & Discrete Diffusion

- Authors : Chieh-Hsin Lai (Sony AI), Subham Sahoo, Dongjun Kim, Yang Song, Yuki Mitsufuji (Sony AI), Stefano Ermon
- Date/Time : June 3rd (Wed) 08:00 - 12:00 (MDT)
- Location : Room 301/302

< Link >
- [CVPR] https://cvpr.thecvf.com/virtual/2026/tutorial/36147

Workshops

Organizer
The 3rd Workshop on Efficient and On-Device Generation (EDGE)

- Organizer: Lingjuan Lyu (Sony AI) as one of organizers
- Date/Time: June 3rd (Wed) 13:00 - 18:00
- Place: Room 210/212

Keynote
The 1st Workshop on Deployment of Foundation Models for Embodied AI
Foundation Models for Robot Navigation, Manipulation, and Planning

- Speaker: Peter Stone (Sony AI/University of Texas at Austin) as one of keynote speakers
- Date/Time: June 3rd (Wed) 09:00 - 09:40 (MDT)
- Place: Place: Room 2E-2H (Four Seasons 2)

Challenge
NTIRE 2026 – New Trends in Image Restoration and Enhancement
Lightweight Neural Networks for Low-Light Image Restoration in NTIRE 2026 Challenge

- Date/Time: June 4th (Thu) 09:00 - 18:00
- Place: Room 207

Paper
The 3rd Workshop on Efficient and On-Device Generation (EDGE)
Training-Free Layout-to-Image Generation with Marginal Attention Constraints

- Authors: Huancheng Chen (Sony AI), Jingtao Li (Sony AI), Weiming Zhuang (Sony AI), Haris Vikalo, Lingjuan Lyu (Sony AI)
- Date/Time: June 3rd (Wed) 13:00 - 18:00
- Place: Room 210/212

Paper
The 3rd Workshop on Efficient and On-Device Generation (EDGE)
On the Limits of Token Reduction for Efficient Unified Vision Language Training

- Authors: Siyi Chen, Weiming Zhuang (Sony AI), Jingtao Li (Sony AI), Lingjuan Lyu (Sony AI)
- Date/Time: June 3rd (Wed) 13:00 - 18:00
- Place: Room 210/212

Paper
Sight and Sound
MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation

- Authors: Akira Takahashi (Sony Group Corporation), Ryosuke Sawata (Sony AI), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: June 4th (Thu) 09:00 - 18:00
- Place: Mile High 1CD

Paper
Sight and Sound
MMAudio-LABEL: Audio Event Labeling via Audio Generation for Silent Video

- Authors: Kazuya Tateishi (Sony Group Corporation), Akira Takahashi (Sony Group Corporation), Atsuo Hiroe (Sony Group Corporation), Hirofumi Takeda (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: June 4th (Thu) 09:00 - 18:00
- Place: Mile High 1CD

Paper
12th International Workshop on Computer Vision in Sports (CVsports)
Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification

- Authors: Shogo Hamano(Sony Group Corporation), Shunya Wakasugi(Sony Group Corporation), Tatsuhito Sato(Sony Group Corporation), Sayaka Nakamura(Sony Group Corporation)
- Date/Time: June 4th (Thu) 09:00 - 17:30
- Place: Room 503

Exhibition Booth
Open Hours

Visit our booth at the exhibition to explore our latest technology firsthand and engage with our team.

Location: # 329 (Floor Plan)
Sony Booth Open Hours:
- June 5th (Fri) 10:00 – 18:00 (MDT)
- June 6th (Sat) 10:00 – 18:00 (MDT)
- June 7th (Sun) 10:00 – 15:00 (MDT)

Exhibition Booth
Technology Presentation

EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer

- Presenter : Munish Monga (Sony Research India)
- Date/Time :
(1) June 5th (Fri) 11:00 - 11:15 (MDT)
(2) June 6th (Sat) 15:30 - 15:45 (MDT)

< Link >
- [Paper] https://arxiv.org/abs/2602.20985

Face Time Traveller: Travel Through Ages Without Losing Identity

- Presenter : Purbayan Kar (Sony Research India)
- Date/Time :
(1) June 5th (Fri) 16:30 - 16:45 (MDT)
(2) June 6th (Sat) 15:15 - 15:30 (MDT)

< Link >
- [Paper] https://arxiv.org/abs/2602.22819

Outplaying Elite Table Tennis Players: A Breakthrough in Autonomous Robotics

- Presenter : Asude Aydin (Sony AI)
- Date/Time :
(1) June 5th (Fri) 11:15 - 11:35 (MDT)
(2) June 6th (Sat) 16:30 - 16:50 (MDT)

< Link >
- https://ace.ai.sony/

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation

- Presenter : Tushar Prakash (Sony Research India)
- Date/Time :
June 6th (Sat) 15:45-16:00 (MDT)

< Link >
- https://cvpr.thecvf.com/virtual/2026/poster/39433
- https://arxiv.org/abs/2601.16210

RewardFlow: Generate Images by Optimizing What You Reward

- Presenter : Tushar Prakash (Sony Research India)
- Date/Time :
June 5th (Fri) 11:45-12:00 (MDT)

< Link >
- https://cvpr.thecvf.com/virtual/2026/poster/37655
- https://arxiv.org/abs/2604.08536

The Principles of Diffusion Models

- Presenter : Chieh-Hsin Lai (Sony AI)
- Date/Time :
(1) June 5th (Fri) 16:00 - 16:15 (MDT)
(2) June 6th (Sat) 12:30 - 12:45 (MDT)

< Link >
- https://the-principles-of-diffusion-models.github.io/

B³-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta–Bernoulli Bayesian Updates

- Presenter : Hiromichi Kamata (Sony Group Corporation)
- Date/Time :
(1) June 5th (Fri) 10:45 - 11:00 (MDT)
(2) June 6th (Sat) 12:45 - 13:00 (MDT)

< Link >
- [Paper] https://arxiv.org/abs/2602.17134
- [Github] https://sony.github.io/B3-Seg-project/

Video-to-Audio Generation: Advancing MMAudio and Expanding Downstream Tasks

- Presenter : Shusuke Takahashi (Sony Group Corporation)
- Date/Time :
(1) June 5th (Fri) 16:15 - 16:30 (MDT)
(2) June 6th (Sat) 17:00 - 17:15 (MDT)

NTIRE 2026 Efficient Low Light Image Enhancement Challenge, 3rd place solution

- Presenter : Teppei Kurita (Sony Semiconductor Solutions Corporation)
- Date/Time :
(1) June 5th (Fri) 16:45 - 17:00 (MDT)
(2) June 6th (Sat) 12:15 - 12:30 (MDT)

< Link >
- [Paper] https://arxiv.org/abs/2605.02212
- [Paper] https://arxiv.org/abs/2604.11071

Exhibition Booth
Technology Demonstrations & Introductions

Book/Poster
The Principles of Diffusion Models

It distills the unified principles of modern diffusion modeling into a systematic account spanning variational, score-based, and flow-based perspectives and fast, controllable diffusion-based generation.

< Link >
- https://the-principles-of-diffusion-models.github.io/

Demonstration
Sony's Creative AI Tools

Experience Sony's AI technologies for content creation, including Search, Generation, and Separation, applicable across a wide range of workflows from Pre-Visualization to Post-Production, Remastering, and Remixing.

Video
Production Ready Face Re-aging using Face Time Traveller

Sony’s face re-aging technology based on Face Time Traveller autonomously alters facial appearance for required age, eliminating the need for costly and time-consuming VFX process

Video
Sony Women in Technology Award with Nature

< Link >
- https://womenintechnology.sony.com/

Follow us on LinkedIn!

Sony Technology - https://www.linkedin.com/company/sony_technology/

Sony Women in Technology Award with Nature

This annual award honors outstanding early to mid-career women researchers pioneering breakthroughs in science, technology, engineering, and mathematics.
Each year, Sony and Nature recognize three researchers with a prize of $250,000 USD each and a chance to showcase work on nature.com.

The application period for the 2027 award is now closed. Eligible CVPR attendees are encouraged to apply next year. Join our newsletter to be the first to know when the next cycle opens.

Career Information

We look forward to working with highly motivated individuals to fill the world with emotion and to pioneer future innovation through dreams and curiosity. If interested, please access our career site and/or consider visiting the Sony booth (Booth#: 329) at the CVPR exhibition area to know more about Sony Group.

Career Site Link: https://www.sony.com/en/SonyInfo/Careers/

Sony Group Technology Portal

You can explore our technology by clicking HERE.

Back to Academic Conferences

Technology