5 papers
InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement
Nikita Kister, Pradyumna YM, István Sárándi +3
Training embodied agents to understand 3D scenes as humans do requires large-scale data of people meaningfully interacting with diverse environments, yet such data is scarce. Real-…
GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction
Pradyumna YM, Yuxuan Xue, Yue Chen +3
Reconstructing physically plausible 3D human-scene interactions (HSI) from a single image currently presents a trade-off: optimization based methods offer accurate contact but are…
Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation
Sunandini Sanyal, Ashish Ramayee Asokan, Suvaansh Bhambri +4
Conventional domain adaptation algorithms aim to achieve better generalization by aligning only the task-discriminative causal factors between a source and target domain. However,…
PwR: Exploring the Role of Representations in Conversational Programming
Pradyumna YM, Vinod Ganesan, Dinesh Kumar Arumugam +7
Large Language Models (LLMs) have revolutionized programming and software engineering. AI programming assistants such as GitHub Copilot X enable conversational programming, narrowi…
Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Pradyumna YM +3
The advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations. Such methods often behave erratically in…