11 papers · 1 filter
Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering
Rohit Kundu, Arindam Dutta, Sarosij Bose +2
Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning th…
CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image
Arindam Dutta, Meng Zheng, Zhongpai Gao +5
Reconstructing clothed humans from a single image is a fundamental task in computer vision with wide-ranging applications. Although existing monocular clothed human reconstruction…
Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes
Sarosij Bose, Arindam Dutta, Sayak Nag +4
Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered…
Repurposing SAM for User-Defined Semantics Aware Segmentation
Rohit Kundu, Sudipta Paul, Arindam Dutta +1
The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific o…
ODES: Domain Adaptation with Expert Guidance for Online Medical Image Segmentation
Md Shazid Islam, Sayak Nag, Arindam Dutta +4
Unsupervised domain adaptive segmentation typically relies on self-training using pseudo labels predicted by a pre-trained network on an unlabeled target dataset. However, the nois…
VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions
Yash Garg, Saketh Bachu, Arindam Dutta +5
Human pose and shape (HPS) estimation methods have been extensively studied, with many demonstrating high zero-shot performance on in-the-wild images and videos. However, these met…