iiinova — where your digital self keeps evolving

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵10/10 Lastly, huge thanks to my co-advisors Niloy and Duygu! For more details check out our paper below- 🌐 Project Website: monetgpt.github.io 📄 Arxiv: arxiv.org/abs/2505.06176

monetgpt.github.io

MonetGPT

010

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵9/10 We quantitaively evaluate on the Adobe5k dataset as well as conduct user studies by expert and novice users. Our evaluations show that MonetGPT outperforms open-source alternatives and performs comparably to Google Photos AutoEnhance (closed-source).

110

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵8/10 Photo editing is subjective 🎨. Our framework adapts to user preference by guidance from natural language tags like ‘vibrant’ or ‘retro vibe’ to produce personalized and stylistically distinct retouching plans from the same input image.

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵7/10 Our puzzle-based training with a 'reasoning as a pathway' approach allows MonetGPT to generate detailed justifications for each edit, delivering truly explainable image retouching

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵6/10 🧩 Puzzle C builds planning capabilities. The model learns to generate a complete, multi-step retouching plan to enhance a photo, structuring its reasoning as a sequence of discrete issues and solutions for clarity and control.

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵5/10 🧩 Puzzle B imparts aesthetic judgement. By ranking professionally edited photos against altered versions, the MLLM learns to recognize the visual characteristics of an optimally adjusted image for any given operation, building an internal aesthetic model.

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵4/10 🧩 Puzzle A builds an understanding of individual operations. The MLLM learns to map visual changes in before/after images to a specific tool and its precise parameter value, effectively learning the semantics of our procedural library.

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵3/10 Our key recipe: MLLMs struggle to predict edit values directly. We solve this by generating rich textual reasoning for each puzzle ✍️. We then fine-tune MonetGPT on this data, creating a 'reasoning pathway' that enables it to regress final adjustment values.

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵2/10 MLLMs lack the visual understanding to plan edits. 🧠 So, we use expert photos as our ground truth and work backward, procedurally creating puzzles by assuming any change to an expert edit makes it less optimal

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵1/10 Excited to share our #SIGGRAPH paper "MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills" 🌟 We explore how to make MLLMs operation-aware by solving visual puzzles and propose a procedural framework for image retouching #MLLM

141

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵10/10 Lastly, huge thanks to my co-advisors Niloy and Duygu! For more details check out our paper below- 🌐 Project Website: monetgpt.github.io 📄 Arxiv: arxiv.org/abs/2505.06176

monetgpt.github.io

MonetGPT

000

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

🧵7/10 Our puzzle-based training with a 'reasoning as a pathway' approach allows MonetGPT to generate detailed justifications for each edit, delivering truly explainable image retouching

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/05/2025

100

Niladri Shekhar Dutt @niladridutt.bsky.social · 10/04/2025

Hi Londoners Join us on April 15 for an evening on Gen AI for 3D at UCL! We have an amazing list of keynote speakers and lightning talks. Register at londongenai.github.io Very excited to co-organize this with Michael and Preddy!

030

Niladri Shekhar Dutt @niladridutt.bsky.social · 27/02/2025

Amazon came pretty late to India and we already had some homegrown companies like Flipkart which now competes with Amazon and is valued at $40B. I think big tech's early access killed homegrown companies. China and to an extent South Korea (Naver) has some great tech companies because of barriers

120

Niladri Shekhar Dutt @niladridutt.bsky.social · 07/02/2025

Who will tell the silicon valley tech bros that it wasn't them alone

040

Reposted by Niladri Shekhar Dutt

Ruchira 🏳️‍🌈 @rayruchira.bsky.social · 17/01/2025

🤔What tasks do we want robots to handle? Are these preferences based on saved time or feelings we associate with the tasks? Introducing Why Automate This?—a study exploring automation preferences across social groups, using feelings & time-spent as key factors. 👇 (1/5)

The image illustrates the evolution of cleaning tasks, balancing time (ATUS) and well-being (ATUS-WB). A central figure considers two options: Manual Labor (vacuum cleaner) and Automated Labor (robotic vacuum), connected by an orange arrow labeled B1-K.

2154

Niladri Shekhar Dutt @niladridutt.bsky.social · 25/11/2024

All the papers I've reviewed still have some reviewers who haven't participated in the discussion/replied to the rebuttal at all. This is true even after the authors have nudged the reviewers a few times already :(

040

Niladri Shekhar Dutt @niladridutt.bsky.social · 24/11/2024

Hey Orion Thanks for the great least. Currently working on RAG, could I be added as well?

010

Niladri Shekhar Dutt @niladridutt.bsky.social · 20/11/2024

While the following feed doesn't depend on likes since it follows a chronological order, I think the discover feed uses likes to tune your experience + recommend popular content

220

Niladri Shekhar Dutt @niladridutt.bsky.social · 20/11/2024

I think keeping likes anonymous allows people to freely like whatever content they want. Not liking reduces post engagement. It also allows one to freely like content without it popping on someone else's feed (I guess this is less of a problem here since only retweets are shown to your network)

3101

Niladri Shekhar Dutt @niladridutt.bsky.social · 20/11/2024

As an author Twitter allows you to see who liked your posts/replies but it's anonymous to others.

161

Reposted by Niladri Shekhar Dutt

Kosta Derpanis @csprofkgd.bsky.social · 19/11/2024

My growing list of #computervision researchers on Bsky. Missed you? Let me know. go.bsky.app/M7HGC3Y

8813242

Niladri Shekhar Dutt @niladridutt.bsky.social · 19/11/2024

Exactly, not getting penalized for external links is a big win!

020

Niladri Shekhar Dutt @niladridutt.bsky.social · 19/11/2024

I've made a starter pack for researchers working in inverse graphics and 3D vision. Let me know if you would like to be added/ want others to be added (more people joining 🦋 everyday) bsky.app/starter-pack...

bsky.app

481

Reposted by Niladri Shekhar Dutt

Tim Baxter @timinclimate.naruresearch.com.au · 18/11/2024

Bluesky tip for newbies: Bluesky has no real algorithm. Likes here do nothing but show the poster that you enjoyed their content. That kindness is always going to be appreciated by creators, but if you want to help to boost something here, you have to repost it so others see it. 🙂

20261629104

Reposted by Niladri Shekhar Dutt

Valentin Deschaintre @vdeschaintre.bsky.social · 18/11/2024

Converted my Graphics Research list to a starter pack (not sure what's the difference though). Let me know who we are missing here :) Here goes! go.bsky.app/ApQNTt2

35817

Niladri Shekhar Dutt @niladridutt.bsky.social · 18/11/2024

Thanks for the list! I've created one for inverse graphics and 3D vision-- bsky.app/starter-pack...

010

Niladri Shekhar Dutt @niladridutt.bsky.social · 18/11/2024

Created a starter pack for researchers working in inverse graphics, 3D vision, and geometry processing. Would love your help to expand this list! go.bsky.app/9uEdjzb

0284

Niladri Shekhar Dutt @niladridutt.bsky.social · 16/11/2024

Finding the perfect banner image is so easy now. Just generated mine with chatGPT/Dall-E 3!

140