Graduated with a PhD in Computer Science @MIT!
Grateful to my advisors and teachers who helped me learn and grow in this journey! Thanks to all my friends and family members for their support.
- Given an image and a selected pixel, our method outputs segment of the image that has the same material as one at the chosen pixel. Materialistic: Selecting Similar Materials in Images is accepted to SIGGRAPH 2023. Paper: arxiv.org/pdf/2305.13291… Webpage: prafullsharma.net/materialistic/
- Excited to share Alchemist! Alchemist enables fine-grained control over material properties of objects in images, specifically roughness, metallic, albedo, and transparency. Website: prafullsharma.net/alchemist arXiv: arxiv.org/abs/2312.02970
- We are releasing the code and demo for Materialistic: Selecting Similar Materials in Images Code: github.com/prafull7/mater… Gradio Demo: materialistic.prafullsharma.net Thanks to my coauthors @vdeschaintre, @JulienPhilip2, @m_gharbi, Bill Freeman, @fredodurand. See you at #SIGGRAPH2023!
- Thrilled to have Alchemist accepted at #CVPR2024 ! Thanks to my collaborators for their contributions and giving me opportunities to learn during this project.Excited to share Alchemist! Alchemist enables fine-grained control over material properties of objects in images, specifically roughness, metallic, albedo, and transparency. Website: prafullsharma.net/alchemist arXiv: arxiv.org/abs/2312.02970
- Replying to @chesscom and @viditchess
- Hear about Materialistic on Thursday at 2 PM in the Material Acquisition session in Room 502 AB! #SIGGRAPH2023
- Researchers use AI to identify similar materials in images: This machine-learning method could assist with robotic scene understanding, image editing, or online recommendation systems. mitsha.re/nVZo50Ouq5B
- Thanks @MIT_CSAIL for covering our work to be presented @CVPR 2024! News article: news.mit.edu/2024/controlle…Researchers from MIT CSAIL and Google created a diffusion model that can change the material properties of objects in images. Their system can tweak both real and AI-generated pictures, potentially helping modify video game models to fit different environments, fine-tune VFX,
