ICVGIP 2025
The Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) is India’s premier conference in Computer Vision, Graphics, Image Processing, and related fields. Since its inception in 1998, ICVGIP served as a biennial international conference until 2021, providing a platform for presenting technological advancements and research findings in these domains. With the significant growth in the community, the conference transitioned to an annual event starting in 2022.
ICVGIP 2025, the 16th conference in this distinguished series, will be organized by IIT Mandi in association with the Indian Unit for Pattern Recognition and Artificial Intelligence (IUPRAI), an affiliate of the International Association for Pattern Recognition (IAPR). ICVGIP continues its mission of fostering a vibrant community of researchers and enthusiasts in computer vision, graphics, and image processing, both in India and globally. Each annual conference strives to uphold this commitment, and ICVGIP 2025 promises to carry forward this tradition.
Nestled in the serene landscapes of Himachal Pradesh, ICVGIP 2025 invites you to engage in cutting-edge research while surrounded by natural beauty that inspires brainstorming, meaningful exchanges, and fruitful collaborations.
The Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) stands as India’s foremost conference in the areas of Computer Vision, Graphics, Image Processing, and allied fields. Established in 1998, it was held biennially until 2021, serving as a premier international platform for presenting technological innovations and research breakthroughs. The 16th edition, ICVGIP 2025, will be hosted by IIT Mandi, in collaboration with the Indian Unit for Pattern Recognition and Artificial Intelligence (IUPRAI), an affiliate of the International Association for Pattern Recognition (IAPR). Recognizing the rapid growth of the community, ICVGIP has been held annually since 2022. The conference is committed to nurturing and strengthening the community of researchers and practitioners in computer vision, graphics, and image processing both within India and globally. We endeavor to uphold this commitment at every edition of the conference.
We invite high-quality, original and unpublished papers in the broad areas of computer vision, graphics, and image processing including, but not limited to:
The Microsoft CMT service is used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.
The review process will be double-blind.
PaperID.pdf before uploading.The following workshops will be held at ICVGIP 2025, on Dec 17, 2025. More information about each workshop is available on the individual webpages, linked to the titles below.
Note that some workshops may also have an associated call for papers.
The following tutorials will be held at ICVGIP 2025, on Dec 17, 2025. More information about each tutorial is available on the individual webpages, linked to the titles below.
The ICVGIP 2025 will host Vision INDIA, a special session dedicated to celebrating and showcasing groundbreaking research by Indian researchers in the fields of Computer Vision, Pattern Recognition, Image Processing, and Graphics. This session will highlight top-tier international papers authored by researchers affiliated with Indian institutions. It offers an exceptional opportunity for these researchers to present their innovative work, originally published at renowned global venues, to the Indian research community and to engage in insightful discussions and knowledge exchange.
We solicit submissions of research in the broad scope of Computer Vision, Pattern Recognition, Image Processing, and Graphics for this session.
The following Eligibility Criteria Apply:
The following conference and journal venues are considered (given the work is within the scope of ICVGIP) for nominations:
Any other equivalent top-tier or prestigious venues not listed above.
Considering the limited slots available for presentation, submissions will be selected by a committee for presentation at ICVGIP-2025.
All nominations must be submitted using the Nomination Link shared above. Please note that submissions via any other method (e.g., emails to organisers) will not be considered.
For any queries please contact:
| Category | Early Registration | Late Registration |
|---|---|---|
| Students (includes accommodation) | INR 5,000 + 18% GST | INR 6,000 + 18% GST |
| Faculty / Researcher | INR 8,000 + 18% GST | INR 9,000 + 18% GST |
| Industry | INR 14,000 + 18% GST | INR 15,000 + 18% GST |
| Category | Early Registration | Late Registration |
|---|---|---|
| Students (includes accommodation) | USD 220 + 18% GST | USD 270 + 18% GST |
| Faculty / Researcher | USD 330 + 18% GST | USD 380 + 18% GST |
Title: *To be updated*
Paul Thompson is a British-American neuroscientist and mathematician who develops advanced AI and mathematical models to map the human brain, integrating large-scale multimodal data to quantify disease processes.
As Associate Director of USC’s Stevens Neuroimaging & Informatics Institute in Los Angeles, he leads national and global projects that combine deep learning, statistical genomics, and multi-resolution structural, diffusion, and functional MRI to dissect brain organization and pathology.
His group builds explainable and generative AI systems—including latent diffusion models, flow-matched transformations, and continuum mechanics frameworks—to characterize normative and pathological brain changes, microstructure, and connectivity across more than 30 diseases. His team also develops vision-language models to support data-driven radiologic interpretation.
Thompson directs the $18M NIH-funded AI4AD initiative on machine learning prediction of Alzheimer’s trajectories and co-founded ENIGMA, the largest brain imaging-genetics consortium worldwide, analyzing data from over 200,000 individuals across 45 countries, with over 2,000 participating scientists.
ENIGMA’s work has produced the largest international MRI-genetic studies of schizophrenia, depression, anorexia, epilepsy, and Parkinson’s, uncovering multiscale biomarkers of disease risk and progression. Ranked among the world’s most cited scientists (h-index=220), Thompson has published over 1,000 papers and delivered keynote lectures such as the Talairach Lecture at OHBM.
His honors include the Gold Medal from the Society of Biological Psychiatry, and with colleagues at NIMHANS (Bangalore), he co-leads the India ENIGMA Initiative to understand drivers of human brain aging and dementia.
Title: Cross-modal generation and understanding of multimodal content
In the first part of the presentation, we will present our work on video generation without annotations or prior object-specific information. Trained on videos of similar objects (e.g. faces, bodies), our method generalizes across the category. Building on this, we introduce a Learnable Game Engine (LGE), trained from monocular annotated videos, that maintains scene and object states and renders environments from controllable viewpoints. Like a game engine, it simulates physics and logic, allowing users to control the game play or use a director mode to guide agents via high-level language and goals, enabled by learned game AI. The second part will investigate the safety and fairness of the current generative models. While most of the existing research focuses on detecting closed sets of biases defined a priori, we tackle the challenge of open-set bias detection in text-to-image generative models. For this we proposed OpenBias, a new pipeline that agnostically identifies and quantifies the severity of biases without access to any precompiled set. We study the behavior of Stable Diffusion 1.5, 2, and XL emphasizing new biases, never investigated before. Via quantitative experiments, we demonstrate that OpenBias agrees with current closed-set bias detection methods and human judgement.
Nicu Sebe is a professor in the University of Trento, Italy, where he is leading the research in the areas of multimedia information retrieval and human-computer interaction in computer vision applications. He received his PhD from the University of Leiden, The Netherlands and has been in the past with the University of Amsterdam, The Netherlands and the University of Illinois at Urbana-Champaign, USA. He was involved in the organization of the major conferences and workshops addressing the computer vision and human-centered aspects of multimedia information retrieval, among which as a General Co-Chair of the IEEE Automatic Face and Gesture Recognition Conference, FG 2008, ACM International Conference on Multimedia Retrieval (ICMR) 2017 and ACM Multimedia 2013. He was a program chair of ACM Multimedia 2011 and 2007, ECCV 2016, ICCV 2017, ICPR 2020 and a general chair of ACM Multimedia 2022. He is a PC of CVPR 2027 and a GC of ACM Multimedia 2027 and ECCV 2028. He is a fellow of ELLIS, IAPR and a Senior member of ACM and IEEE. He is the co-editor in chief of Computer Vision and Image Understanding journal.
*To be updated*
Srinath Sridhar is the John E. Savage Assistant Professor of Computer Science at Brown University, where he leads the Interactive 3D Vision & Learning Lab (https://ivl.cs.brown.edu). He received his PhD at the Max Planck Institute for Informatics and was subsequently a postdoctoral researcher at Stanford. His research interests are in 3D computer vision and artificial intelligence. Specifically, his group builds foundational methods for 3D spatiotemporal (4D) visual understanding of the world including objects in it, humans in motion, and human-object interactions, with applications ranging from robotics to mixed reality. He is the recipient of an NSF CAREER award, a Google Research Scholar award, and his work received a Best Student Paper award at WACV and a Best Paper Honorable Mention at Eurographics. He spends part of his time as an Amazon Scholar and a visiting faculty at the Indian Institute of Science (IISc).
The Indian Conference on Computer Vision, Graphics, and Image Processing (ICVGIP) stands as India's premier forum for these dynamic fields. Since its inception in 1998, ICVGIP has been a crucial platform for showcasing cutting-edge technological advancements and pivotal research findings. The upcoming 16th ICVGIP 2025 is proudly hosted by IIT Mandi in collaboration with the Indian Unit for Pattern Recognition and Artificial Intelligence (IUPRAI), an affiliate of the esteemed International Association for Pattern Recognition (IAPR). Renowned for nurturing a vibrant community of researchers and enthusiasts both domestically and internationally, ICVGIP transitioned to an annual cadence in 2022, a testament to the significant expansion of this community. ICVGIP 2025 continues to embody our unwavering commitment to the evolving landscapes of computer vision, graphics, and image processing. The conference offers a dynamic environment for academics and industry experts to converge, exchange insights, and explore the latest innovations shaping these domains.
ICVGIP has consistently cultivated strong industry relationships and actively encourages engagement from diverse sectors. The conference presents multifaceted opportunities for industry participation, spanning the technical program, specialized research symposiums, and exhibitions. By engaging with ICVGIP as a sponsor, organizations not only gain significant visibility but also acquire the chance to influence the trajectory of these rapidly progressing fields. We earnestly encourage companies and R&D laboratories to present their groundbreaking work and actively connect with the community at ICVGIP. This engagement is not only invaluable for fostering networking and knowledge dissemination but also pivotal in molding the future directions of computer vision, graphics, and image processing. We offer a spectrum of sponsorship tiers, detailed below, each accompanied by a corresponding allocation of complimentary registrations as outlined below:
Sponsorship cost
INR 10 Lakh
Sponsorship cost
INR 5 Lakh
Sponsorship cost
INR 3 Lakh
Sponsorship cost
INR 1 Lakh
Sponsorship cost
INR 50 Thousand
Sponsorship cost
Contact Sponsors
IIT Mandi
IIT Delhi
IIT Delhi
IIIT Bangalore
IIIT Hyderabad
IIT Madras
IIT Mandi
IIT Mandi
IIT Mandi
IIT Mandi
IIT Mandi
IIT Mandi
IIT Mandi
IIT Mandi
IIT Ropar
IIT Hyderabad
IIT Kharagpur
IIT Gandhinagar
IIT Hyderabad
IIIT Hyderabad
IIT Jodhpur
IIT Kharagpur
IIT BHU
IIT Ropar
Walmart Global Tech
IISc Bangalore
Ashoka University
IBM Research
The conference will be held at IIT Mandi's North campus in Kamand, Mandi District, Himachal Pradesh, India. Please read about the geography of this location here. The location is very close to a number of very popular tourist attractions.
| Hotel Name | Location | Contact No. | Room Charges per night |
|---|---|---|---|
| Hotel Parashar Valley View | Kataula, Mandi - 5 km from campus | 9816296621 | INR 1700 + GST |
| Hotel Name | Location | Link |
|---|---|---|
| Munish Resorts | Mandi City | Click here |
| Raj Mahal Palace | Mandi City | Click here |
| Hotel Park View | Mandi City | Click here |
| The Regent Palms Hotel | Mandi City | Click here |
| Visco Resorts | Mandi City | Click here |
| Hotel River Bank | Mandi City | Click here |
| Classio | Mandi City | Click here |
IIT Mandi is surrounded by several scenic and culturally rich tourist spots, perfect for exploration.
A serene lake with views of the Dhauladhar range, located 32 km from IIT Mandi. Perfect for a peaceful retreat in nature.
A religiously significant and scenic lake located 45 km from IIT Mandi, popular with both tourists and pilgrims.
Famous hill stations known for adventure, natural beauty, and vibrant culture, located around 55-95 km from IIT Mandi.
Renowned for paragliding and Tibetan monasteries, located 75 km from IIT Mandi.
A tranquil valley with lush green landscapes, located around 70 km from IIT Mandi.
A breathtaking waterfall in the Lahaul region, located about 40 km from Manali.
IIT Mandi North Campus
Parashar Road, Tehsil Sadar, Near Kataula, Kamand, Himachal Pradesh 175005
