6 papers
Foundry: Distilling 3D Foundation Models for the Edge
Guillaume Letellier, Siddharth Srivastava, Frédéric Jurie +1
Foundation models pre-trained with self-supervised learning (SSL) on large-scale datasets have become powerful general-purpose feature extractors. However, their immense size and c…
Image-Text Knowledge Modeling for Unsupervised Multi-Scenario Person Re-Identification
Zhiqi Pang, Lingling Zhao, Yang Liu +2
We propose unsupervised multi-scenario (UMS) person re-identification (ReID) as a new task that expands ReID across diverse scenarios (cross-resolution, clothing change, etc.) with…
Styleclone: Face Stylization with Diffusion Based Data Augmentation
Neeraj Matiyali, Siddharth Srivastava, Gaurav Sharma
We present StyleClone, a method for training image-to-image translation networks to stylize faces in a specific style, even with limited style images. Our approach leverages textua…
RephraseTTS: Dynamic Length Text based Speech Insertion with Speaker Style Transfer
Neeraj Matiyali, Siddharth Srivastava, Gaurav Sharma
We propose a method for the task of text-conditioned speech insertion, i.e. inserting a speech sample in an input speech sample, conditioned on the corresponding complete text tran…
Preserve Anything: Controllable Image Synthesis with Object Preservation
Prasen Kumar Sharma, Neeraj Matiyali, Siddharth Srivastava +1
We introduce \textit{Preserve Anything}, a novel method for controlled image synthesis that addresses key limitations in object preservation and semantic consistency in text-to-ima…
OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
Siddharth Srivastava, Gaurav Sharma
We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image,…