2 citations · 3 across the 10 of their papers we have counts for
11 papers
SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera
Shriram Damodaran, Soumyaratna Debnath, Cheston Tan +1
Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use of Multi-modal Large Language Mod…
AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation
Soumyaratna Debnath, Weiming Zhang, Shriram Damodaran +2
Spherical Transformers have emerged as a promising framework for panoramic semantic segmentation (PASS) by operating directly on spherical geometry and alleviating projection-induc…
EAGOR: Embodied Reasoning in Omni-direction
Shriram Damodaran, Soumyaratna Debnath, Yan Wu +2
Omni-directional (360°) cameras provide embodied agents with a holistic view of their surroundings, making them suited for directional reasoning in tasks such as navigation and obj…
VL2Spike: Spike-driven Distillation from VLMs for Low-Power Visual Perception in Embodied AI
Zinan Liu, Eric Zheng, Soumyaratna Debnath +3
Spiking neural networks (SNNs) are brain-inspired, event-driven models that compute with sparse spikes, which enables highly efficient visual perception in resource-constrained emb…
LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models
Soumyaratna Debnath, Bui Duc Manh, Zinan Liu +1
Vision-Language Models (VLMs) typically assume a uniform spatial fidelity across the entire field of view of visual inputs, dedicating equal precision to even the uninformative reg…
Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
Bui Duc Manh, Soumyaratna Debnath, Zetong Zhang +6
Recent advances in agentic AI have led to systems capable of autonomous task execution and language-based reasoning, yet their spatial reasoning abilities remain limited and undere…
COT-AD: Cotton Analysis Dataset
Akbar Ali, Mahek Vyas, Soumyaratna Debnath +7
This paper presents COT-AD, a comprehensive Dataset designed to enhance cotton crop analysis through computer vision. Comprising over 25,000 images captured throughout the cotton g…
RASP: Revisiting 3D Anamorphic Art for Shadow-Guided Packing of Irregular Objects
Soumyaratna Debnath, Ashish Tiwari, Kaustubh Sadekar +1
Recent advancements in learning-based methods have opened new avenues for exploring and interpreting art forms, such as shadow art, origami, and sketch art, through computational m…
DeepSTEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans
Shashikant Verma, Harish Katti, Soumyaratna Debnath +2
Maintaining a consistent identity across video frames while estimating pose is crucial for downstream tasks such as behavior analysis and action recognition, yet existing pipelines…
L3D-Pose: Lifting Pose for 3D Avatars from a Single Camera in the Wild
Soumyaratna Debnath, Harish Katti, Shashikant Verma +1
While 2D pose estimation has advanced our ability to interpret body movements in animals and primates, it is limited by the lack of depth information, constraining its application…
ScribGen: Generating Scribble Art Through Metaheuristics
Soumyaratna Debnath, Ashish Tiwari, Shanmuganathan Raman
Art has long been a medium for individuals to engage with the world. Scribble art, a form of abstract visual expression, features spontaneous, gestural strokes made with pens or br…