CVPR 2025

CVPR 2025 (The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025) is the premier annual computer vision, and AI event. More than 10,000 professionals come 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 a Platinum Sponsor of CVPR 2025.
We look forward to this year's exciting sponsorship and exhibition opportunities, featuring a variety of ways to connect with participants in person.

Exhibition Booth
Open Hours

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

Location: #1517 (Hall B)
Sony Booth Open Hours:
- June 13th (Fri) 10:00 - 18:30 (CDT)
- June 14th (Sat) 10:00 - 18:30 (CDT)
- June 15th (Sun) 10:00 - 15:00 (CDT)

Exhibition Booth
Technology Presentations

Argus: A Compact and Versatile Foundation Model for Vision

Presenter : Chen Chen
Date/Time :
- June 13th (Fri) 16:30-16:45
- June 14th (Sat) 10:15-10:30
Link :
- https://cvpr.thecvf.com/virtual/2025/poster/32530
- https://www.cs.utexas.edu/~pstone/Papers/bib2html-links/vfm_cvpr2025.pdf

Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision

Presenter : Taichi Nishimura
Date/Time :
- June 13th (Fri) 10:45-11:00
- June 14th (Sat) 11:30-11:45
Link :
- https://cvpr.thecvf.com/virtual/2025/poster/34183
- https://biscue5.github.io/egoscaler-project-page/

Generative AI for Content Creation

Presenter : Takashi Shibuya
Date/Time :
- June 13th (Fri) 10:15-10:30
- June 14th (Sat) 16:00-16:15
Link :
- https://github.com/sony/creativeai
- https://ai.sony/blog/Unlocking-the-Future-of-Video-to-Audio-Synthesis-Inside-the-MMAudio-Model/

Matrix-Free Shared Intrinsics Bundle Adjustment

Presenter : Daniel Safari
Date/Time :
- June 13th (Fri) 14:30-14:45
- June 14th (Sat) 14:15-14:30
Link :
- https://cvpr.thecvf.com/virtual/2025/poster/34273

MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities

Presenter : Gianluca Agresti, Federico Lincetto
Date/Time :
- June 13th (Fri) 10:30-10:45
- June 15th (Sun) 11:30-11:45
Link :
- https://lttm.github.io/MultimodalStudio/

NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectrics

Presenter : Sho Nitta
Date/Time :
- June 13th (Fri) 11:30-11:45
- June 14th (Sat) 16:15-16:30
Link :
- https://arxiv.org/abs/2411.10189

Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising

Presenter : Feiran Li
Date/Time :
- June 14th (Sat) 16:30-16:45
- June 15th (Sun) 10:15-10:30
Link :
- https://cvpr.thecvf.com/virtual/2025/poster/32600
- https://github.com/SonyResearch/raw_image_denoising

Perceptual Video Compression with Neural Wrapping

Presenter : Russell Anam
Date/Time :
- June 13th (Fri) 11:45-12:00
- June 15th (Sun) 11:45-12:00
Link :
- https://cvpr.thecvf.com/virtual/2025/poster/34427

ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge

Presenter : Radu Berdan
Date/Time :
- June 13th (Fri) 16:15-16:30
- June 15th (Sun) 10:30-10:45
Link :
- https://cvpr.thecvf.com/virtual/2025/poster/34591
- https://arxiv.org/abs/2503.03782

Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget

Presenter : Jingtao Li
Date/Time :
- June 13th (Fri) 16:00-16:15
- June 14th (Sat) 10:30-10:45
Link :
- https://cvpr.thecvf.com/virtual/2025/poster/32631
- https://arxiv.org/abs/2407.15811

VinaBench: Benchmark for Faithful and Consistent Visual Narratives

Presenter : Silin Gao
Date/Time :
- June 14 (Sat) 15:45-16:00
- June 15 (Sun) 10:45-11:00
Link :
https://cvpr.thecvf.com/virtual/2025/poster/33363
https://arxiv.org/abs/2503.20871
https://www.aicrowd.com/challenges/commonsense-persona-grounded-dialogue-challenge-2025

Exhibition Booth
Technology Demonstrations & Introductions

Spectrum-based Perception: Embedded-Friendly Spectral Solution

Our multispectral sensing solution derives image data up to 41 wavelengths (from 450 nm to 850 nm, in 10 nm intervals) simultaneously by just one shot. The solution is composed of Sony’s 1st multispectral sensor (IMX454) with 8 types of on-chip filter and the specially designed signal processing software.
As the solution makes it possible to distinguish slight color differences compared to RGB camera, it can be used in applications such as material sorting, contaminant detection inspection, and quality management.

Demonstrators : Shigeyuki Baba, Hiroki Yamashita
Date/Time :
- June 13th (Fri) 10:00-13:00, 15:30-18:30 (CDT)
- June 14th (Sat) 10:00-13:00, 15:30-18:30 (CDT)
- June 15th (Sun) 10:00-13:00, 14:00-15:00 (CDT)
Link :
- https://www.sony-semicon.com/en/technology/industry/multispectral.html
- https://www.sony-semicon.com/en/products/is/industry/multispectral.html

NeuroTouch: Live Demonstration: NeuroTouch - A Neuromorphic Vision-based Tactile Sensor for Real-Time Gesture Recognition

We propose to demonstrate NeuroTouch, a vision-based tactile sensor that combines a highly deformable dome-shaped soft material with an integrated neuromorphic camera, leveraging frame-based and event-based vision for multi-finger gesture detection. Our approach transforms an elastic body into a rich and nuanced interactive controller by tracking markers printed on its surface with event-based methods and classifying the trajectories of the points into one of five gesture types with a corresponding intensity. We will demonstrate this novel control interface with a simple video game, highlighting the potential of soft controllers for entertainment applications.

Demonstrator : Valentina Cavinato
Date/Time :
- June 13th (Fri) 10:30-12:30 (CDT)
- June 14th (Sat) 12:30-14:30 (CDT)
- June 15th (Sun) 10:00-12:00 (CDT)
Link :
- https://arxiv.org/html/2501.19174v1
- https://www.youtube.com/watch?v=wUlGerb8I68

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to single-modality training conditioned on (limited) video data only, MMAudio is jointly trained with larger-scale, readily available text-audio data to learn to generate semantically aligned high-quality audio samples. Additionally, we improve audio-visual synchrony with a conditional synchronization module that aligns video conditions with audio latents at the frame level. Trained with a flow matching objective, MMAudio achieves new video-to-audio state-of-the-art among public models in terms of audio quality, semantic alignment, and audio-visual synchronization, while having a low inference time (1.23s to generate an 8s clip) and just 157M parameters. MMAudio also achieves surprisingly competitive performance in text-to-audio generation, showing that joint training does not hinder single-modality performance.

Link :
- https://github.com/hkchengrex/MMAudio
- https://ai.sony/blog/Unlocking-the-Future-of-Video-to-Audio-Synthesis-Inside-the-MMAudio-Model/

EgoScaler: Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision

Learning to use tools or objects in common scenes, particularly handling them in various ways as instructed, is a key challenge for developing interactive robots. Training models to generate such manipulation trajectories requires a large and diverse collection of detailed manipulation demonstrations for various objects, which is nearly unfeasible to gather at scale. In this paper, we propose a framework that leverages large-scale ego- and exo-centric video datasets — constructed globally with substantial effort — of Exo-Ego4D to extract diverse manipulation trajectories at scale. From these extracted trajectories with the associated textual action description, we develop trajectory generation models based on visual and point cloudbased language models. In the recently proposed egocentric vision-based in-a-quality trajectory dataset of HOT3D, we confirmed that our models successfully generate valid object trajectories, establishing a training dataset and baseline models for the novel task of generating 6DoF manipulation trajectories from action descriptions in egocentric vision. Our dataset and code: https://biscue5.github.io/egoscaler-project-page/

Link :
- https://cvpr.thecvf.com/virtual/2025/poster/34183
- https://biscue5.github.io/egoscaler-project-page/

GT Sophy

Gran Turismo Sophy (GT Sophy) represents the future of racing AI—an advanced driving agent developed in partnership with Sony AI and Sony Interactive Entertainment.

First unveiled as GT Sophy 2.0 in Gran Turismo 7 in November 2023, the intelligent racer will evolve once again with the release of Update 1.57. This next iteration, called GT Sophy 2.1, will be available exclusively for the PlayStation®5 version only.

With this update, GT Sophy 2.1 steps into new territory. GT Sophy was previously limited to Quick Race events with preset configurations, but this update allows players to select GT Sophy for individual Rival Cars. Players gain more control, with the ability to fine-tune race settings such as tire wear, fuel consumption, and even stage one-make races using vehicles from their own garages. (Note: Some settings may remain restricted.)

Link :
- https://www.gran-turismo.com/us/news/00_4957003.html

Corporate Information

Introduction : Shawn Barrett
Date/Time :
- June 13th (Fri) 12:15-12:30 (CDT)
- June 14th (Sat) 10:45-11:00 (CDT)

Sony's Technical Programs at CVPR 2025

Poster Sessions

Argus: A Compact and Versatile Foundation Model for Vision

- Authors: Weiming Zhuang (Sony AI), Chen Chen (Sony AI), Zhizhong Li (Sony AI), Sina Sajadmanesh (Sony AI), Jingtao Li (Sony AI), Jiabo Huang (Sony AI), Vikash Sehwag (Sony AI), Vivek Sharma (Sony AI), Hirotaka Shinozaki (Sony Semiconductor Solutions Corporation), Felan Carlo Garcia (Sony Semiconductor Solutions Corporation), Yihao Zhan (Sony Semiconductor Solutions Corporation), Naohiro Adachi (Sony Semiconductor Solutions Corporation), Ryoji Eki (Sony Semiconductor Solutions Corporation), Michael Spranger (Sony AI), Peter Stone (Sony AI/University of Texas at Austin), Lingjuan Lyu (Sony AI)
- Date/Time: [Poster Session 1] June 13th (Fri) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #408

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/32530
- https://www.cs.utexas.edu/~pstone/Papers/bib2html-links/vfm_cvpr2025.pdf

Classifier-Free Guidance inside the Attraction Basin May Cause Memorization

- Authors: Anubhav Jain, Yuya Kobayashi (Sony AI), Takashi Shibuya (Sony AI), Yuhta Takida (Sony AI), Nasir Memon, Julian Togelius, Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: [Poster Session 3] June 14th (Sat) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #212

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/32782
- https://arxiv.org/abs/2411.16738

CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI

- Authors: Siyuan Cheng, Lingjuan Lyu (Sony AI), Zhenting Wang, Xiangyu Zhang, Vikash Sehwag (Sony AI)
- Date/Time: [Poster Session 3] June 14th (Sat) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #268

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34282
- https://arxiv.org/abs/2503.18286

EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering

- Authors: Toshiya Yura (Sony Semiconductor Solutions Corporation), Ashkan Mirzaei, Igor Gilitschenski
- Date/Time: [Poster Session 6] June 15th (Sun) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #70

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/33721
- https://arxiv.org/abs/2412.07293

Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision

- Authors: Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura (Sony Interactive Entertainment), Shinsuke Mori
- Date/Time: [Poster Session 4] June 14th (Sat) 17:00 - 19:00 (CDT)
- Place: ExHall D Poster #151

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34183
- https://biscue5.github.io/egoscaler-project-page/

Matrix-Free Shared Intrinsics Bundle Adjustment

- Authors: Daniel Safari (Sony Semiconductor Solutions Corporation)
- Date/Time: [Poster Session 6] June 15th (Sun) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #83

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34273

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

- Authors: Ho Kei Cheng, Masato Ishii (Sony AI), Akio Hayakawa (Sony AI), Takashi Shibuya (Sony AI), Alexander Schwing, Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: [Poster Session 6] June 15th (Sun) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #260

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/33479
- https://arxiv.org/abs/2412.15322
- https://github.com/hkchengrex/MMAudio
- https://huggingface.co/spaces/hkchengrex/MMAudio

MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities

- Authors: Federico Lincetto, Gianluca Agresti (Sony Europe B.V.), Mattia Rossi (Sony Europe B.V.), Pietro Zanuttigh
- Date/Time: [Poster Session 3] June 14th (Sat) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #29

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34722
- https://arxiv.org/abs/2503.19673
- https://lttm.github.io/MultimodalStudio/

NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectrics

- Authors: Chenhao Li (Sony Semiconductor Solutions Corporation, Osaka Universiy), Taishi Ono (Sony Europe B.V), Takeshi Uemori (Sony Semiconductor Solutions Corporation), Sho Nitta (Sony Semiconductor Solutions Corporation), Hajime Mihara (Sony Semiconductor Solutions Corporation), Alexander Gatto (Sony Europe B.V), Hajime Nagahara, Yusuke Moriuchi (Sony Semiconductor Solutions Corporation)
- Date/Time: [Poster Session 6] June 15th (Sun) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #31

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/35142
- https://arxiv.org/abs/2411.10189

Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising

- Authors: Feiran Li (Sony Research), Haiyang Jiang, Daisuke Iso (Sony Research)
- Date/Time: [Poster Session 2] June 13th (Fri) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #24

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/32600
- https://github.com/SonyResearch/raw_image_denoising

On-Device Self-Supervised Learning of Low-Latency Monocular Depth from Only Events

- Authors: Jesse Hagenaars, Yilun Wu, Federico Paredes-Valles (EUISPC, Sony Semiconductor Solutions Europe,, Sony Europe B.V), Stein Stroobants, Guido de Croon
- Date/Time: [Poster Session 2] June 13th (Fri) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #24

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/35185
- https://arxiv.org/abs/2412.06359

Perceptual Video Compression with Neural Wrapping

- Authors: Aaron Chadha (Sony Interactive Entertainment), Umar Khan (Sony Interactive Entertainment), Russell Anam (Sony Interactive Entertainment), Yiannis Andreopoulos (Sony Interactive Entertainment)
- Date/Time: [Poster Session 4] June 14th (Sat) 17:00 - 19:00 (CDT)
- Place: ExHall D Poster #185

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34427

Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance

- Authors: Sanchayan Santra (Sony Research India), Vishal Chudasama (Sony Research India), Pankaj Wasnik (Sony Research India), Vineeth Balasubramanian
- Date/Time: [Poster Session 1] June 13th (Fri) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #287

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34087
- https://arxiv.org/pdf/2503.00147

ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge

- Authors: Radu Berdan (Sony AI), Beril Besbinar (Sony AI), Christoph Reinders, Junji Otsuka (Sony Group Corporation), Daisuke Iso (Sony AI)
- Date/Time: [Poster Session 3] June 14th (Sat) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #115

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34591
- https://arxiv.org/abs/2503.03782

Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety

- Authors: Ronghang Zhu, Mengxuan Hu, Weiming Zhuang (Sony AI), Lingjuan Lyu (Sony AI), Xiang Yu, Sheng Li
- Date/Time: [Poster Session 5] June 15th (Sun) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #445

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/32745

Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models

- Authors: Jie Ren, Kangrui Chen, Yingqian Cui, Shenglai Zeng, Hui Liu, Yue Xing, Jiliang Tang, Lingjuan Lyu (Sony AI)
- Date/Time: [Poster Session 6] June 15th (Sun) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #248

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/34826
- https://arxiv.org/abs/2406.14855

Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget

- Authors: Vikash Sehwag (Sony AI), Xianghao Kong, Jingtao Li (Sony AI), Michael Spranger (Sony AI), Lingjuan Lyu (Sony AI)
- Date/Time: [Poster Session 6] June 15th (Sun) 16:00 - 18:00 (CDT)
- Place: ExHall D Poster #232

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/32631
- https://arxiv.org/abs/2407.15811

VinaBench: Benchmark for Faithful and Consistent Visual Narratives

- Authors: Silin Gao, Sheryl Mathew, Li Mi, Sepideh Mamooler, Mengjie Zhao (Sony Group Corporation), Hiromi Wakaki (Sony Group Corporation), Yuki Mitsufuji (Sony Group Corporation), Syrielle Montariol, Antoine Bosselut
- Date/Time: [Poster Session 1] June 13th (Fri) 10:30 - 12:30 (CDT)
- Place: ExHall D Poster #259

< Link >
- https://cvpr.thecvf.com/virtual/2025/poster/33363
- https://arxiv.org/abs/2503.20871

Workshops

Organizer
Test-time Scaling for Computer Vision

- As an organizer: Lingjuan Lyu (Sony AI)
- Date/Time: June 12th (Thu) 09:00 - 12:00 (CDT)
- Place: 109

< Link >
- https://viscale.github.io/

Organizer
4th Workshop on Federated Learning for Computer Vision

- As an organizer: Lingjuan Lyu (Sony AI)
- Date/Time: June 11th (Wed) 09:00 - 17:00 (CDT)
- Place: 103 B

< Link >
- https://fedvision.github.io/fedvision2025/

5th International Workshop on Event-based Vision
Towards Low-Latency Event-based Obstacle Avoidance on a FPGA-Drone

- Authors: Pietro Bonazzi, Christian Vogt, Michael Jost, Lyes Khacef (Sony Semiconductor Solutions Europe, Sony Europe B.V.), Federico Paredes-Valles (Sony Semiconductor Solutions Europe, Sony Europe B.V.), Michele Magno
- Date/Time: June 12th (Thu) 09:00 - 17:00 (CDT)
- Place: Grand C2

< Link >
- https://tub-rip.github.io/eventvision2025/
- https://arxiv.org/pdf/2504.10400

5th International Workshop on Event-based Vision
Live Demonstration: NeuroTouch - A Neuromorphic Vision-based Tactile Sensor for Real-Time Gesture Recognition

- Authors: Valentina Cavinato, Kirk Scheper, Victor Hoffman
- Date/Time: June 12th (Thu) 09:00 - 17:00 (CDT)
- Place: Grand C2

< Link >
- https://tub-rip.github.io/eventvision2025/
- https://arxiv.org/html/2501.19174v1

2nd Workshop on Human Motion Generation (HuMoGen)
MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training

- Authors: Kengo Uchida (Sony AI), Takashi Shibuya (Sony AI), Yuhta Takida (Sony AI), Naoki Murata (Sony AI), Julian Tanke (Sony AI), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: June 11th (Wed) 13:00 - 17:00 (CDT)
- Place: 110 B

< Link >
- https://humogen.github.io/
- https://arxiv.org/abs/2406.01867

2nd Workshop on Human Motion Generation (HuMoGen)
Dyadic Mamba: Long-term Dyadic Human Motion Synthesis

- Authors: Julian Tanke (Sony AI), Takashi Shibuya (Sony AI), Kengo Uchida (Sony AI), Koichi Saito (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: June 11th (Wed) 13:00 - 17:00 (CDT)
- Place: 110 B

< Link >
- https://humogen.github.io/
- https://arxiv.org/abs/2505.09827

Second Joint Egocentric Vision (EgoVis) Workshop
Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision

- Authors: Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura (Sony Interactive Entertainment), Shinsuke Mori
- Date/Time: June 12th (Thu) 09:00 - 17:00 (CDT)
- Place: Grand B1

< Link >
- https://egovis.github.io/cvpr25/
- https://biscue5.github.io/egoscaler-project-page/

Sight and Sound
SAVGBench: Benchmarking Spatially Aligned Audio-Video Generation

- Authors: Kazuki Shimada (Sony AI), Christian Simon (Sony Group Corporation), Takashi Shibuya (Sony AI), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: June 11th (Wed) 09:00 - 12:00 (CDT)
- Place: 211

< Link >
- https://sightsound.org/
- https://arxiv.org/abs/2412.13462

Event Report

Sony had a strong presence at CVPR 2025 in Nashville, US, where we introduced our latest research and technologies.
We were delighted to welcome many visitors to our booth and engage in meaningful conversations with researchers and professionals from around the world.
Our Technology Blog captures these moments along with details of our accepted papers.

Visit to learn more about our contributions:
https://www.sony.com/en/SonyInfo/technology/stories/entries/CVPR2025_report/

Follow us on LinkedIn!

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

Sony Women in Technology Award with Nature

Career Information

Sony Group Technology Portal

You can explore our technology by clicking HERE.