Arindam Dutta

5

Papers

4

Total Citations

Papers (5)

Towards Source-Free Machine Unlearning

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions

CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image

Uncertainty-Aware Diffusion-Guided Refinement of 3D Scenes