AIConfPaper
← Search

Ravi Kiran Sarvadevabhatla

7 accepted papers

2026

M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA

Venkata Kesav Venna, Sai Madhusudan Gunda, Jyothi Swaroopa Jinka, Hrithik Sagar Rachakonda, Anirudh Srinivasan, Ravi Kiran Sarvadevabhatla
CVPR 2026

**Document QA** requires not only accurate answers but also identifying where each answer is grounded on the page. Most models treat the task as text-only generation, while existing answer grounding methods generate coarse bounding boxes that fail to capture curved text. We introduce **M3Grounder, a

Cited by 0Source ↗Scholar ↗
2026

SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation

Vaibhav Agrawal, Rishubh Parihar, Pradhaan S Bhat, Ravi Kiran Sarvadevabhatla, Venkatesh Babu Radhakrishnan
CVPR 2026

We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded objects with depth-consistent geometry and scale. While existing methods can generate realistic scenes that follow input layouts, they ofte

Cited by 0Source ↗Scholar ↗
2025

RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives

Chirag Parikh, Deepti Rawat, Rakshitha R. T., Tathagata Ghosh, Ravi Kiran Sarvadevabhatla
CVPR 2025poster

We introduce RoadSocial, a large-scale, diverse VideoQA dataset tailored for generic road event understanding from social media narratives. Unlike existing datasets limited by regional bias, viewpoint bias and expert-driven annotations, RoadSocial captures the global complexity of road events with v…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Sketchtopia: A Dataset and Foundational Agents for Benchmarking Asynchronous Multimodal Communication with Iconic Feedback

Mohd Hozaifa Khan, Ravi Kiran Sarvadevabhatla
CVPR 2025poster

We introduce Sketchtopia, a large-scale dataset and AI framework designed to explore goal-driven, multimodal communication through asynchronous interactions in a Pictionary-inspired setup. Sketchtopia captures natural human interactions, including freehand sketches, open-ended guesses, and iconic fe…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic

Chirag Parikh, Rohit Saluja, C. V. Jawahar, Ravi Kiran Sarvadevabhatla
ICRA 2024poster

Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and the ego vehicle’s driving behavior for safe and efficient navigation. This is particularly critical in developing countries where traffic situations are often dense and unstru…

Cited by 3Source ↗code ↗Scholar ↗
2020

Topological Mapping for Manhattan-like Repetitive Environments

Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya, Udit Singh Parihar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna
ICRA 2020poster

We showcase a topological mapping framework for a challenging indoor warehouse setting. At the most abstract level, the warehouse is represented as a Topological Graph where the nodes of the graph represent a particular warehouse topological construct (e.g. rackspace, corridor) and the edges denote…

Cited by 12Source ↗code ↗Scholar ↗
2017

DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data

Swaminathan Gurumurthy, Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu
CVPR 2017poster

A class of recent approaches for generating images, called Generative Adversarial Networks (GAN), have been used to generate impressively realistic images of objects, bedrooms, handwritten digits and a variety of other image modalities. However, typical GAN-based approaches require large amounts of…

Cited by 377PDF ↗Scholar ↗