107 citations · 220 across the 24 of their papers we have counts for
31 papers
GazeDiT: Gaze-Accurate Diffusion Image Generation for Eye Tracking via Spatial Conditioning
Dongze Wu, David Colmenares, Fengting Yang +4
Diffusion models are increasingly used to generate synthetic training data, but precise label control remains difficult when the conditioning signal is low-dimensional and coarse.…
GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction
Corentin Dumery, David Colmenares, Alexander Fix +3
Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real data collection is costly a…
Rapidly deploying on-device eye tracking by distilling visual foundation models
Cheng Jiang, Jogendra Kundu, David Colmenares +4
Eye tracking (ET) plays a critical role in augmented and virtual reality applications. However, rapidly deploying high-accuracy, on-device gaze estimation for new products remains…
Digitally Prototype Your Eye Tracker: Simulating Hardware Performance using 3D Synthetic Data
Esther Y. H. Lin, Yimin Ding, Jogendra Kundu +3
Eye tracking (ET) is a key enabler for Augmented and Virtual Reality (AR/VR). Prototyping new ET hardware requires assessing the impact of hardware choices on eye tracking performa…
Balancing Act: Distribution-Guided Debiasing in Diffusion Models
Rishubh Parihar, Abhijnya Bhat, Abhipsa Basu +3
Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative ap…
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,…
Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation
Sunandini Sanyal, Ashish Ramayee Asokan, Suvaansh Bhambri +3
Conventional Domain Adaptation (DA) methods aim to learn domain-invariant feature representations to improve the target adaptation performance. However, we motivate that domain-spe…
Subsidiary Prototype Alignment for Universal Domain Adaptation
Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni +3
Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer between two datasets with domain-shift as well as category-shift. The goal is to categorize unlabel…
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation
Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni +3
The prime challenge in unsupervised domain adaptation (DA) is to mitigate the domain shift between the source and target domains. Prior DA works show that pretext tasks could be us…
Balancing Discriminability and Transferability for Source-Free Domain Adaptation
Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri +4
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discrimina…
Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Anirudh Jamkhandi +4
Available 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. Barring synthetic or in-studio domai…
Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery
Mugalodi Rakesh, Jogendra Nath Kundu, Varun Jampani +1
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquir…
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…
Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation
Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri +2
Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting which considers a single labeled source domain against a compound of multi-modal unlabeled targ…
Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
Jogendra Nath Kundu, Akshay Kulkarni, Amit Singh +2
Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unl…
Your Classifier can Secretly Suffice Multi-Source Domain Adaptation
Naveen Venkat, Jogendra Nath Kundu, Durgesh Kumar Singh +2
Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain, under a domain-shift. Existing m…
Class-Incremental Domain Adaptation
Jogendra Nath Kundu, Rahul Mysore Venkatesh, Naveen Venkat +2
We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning…
Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation
Jogendra Nath Kundu, Ambareesh Revanur, Govind Vitthal Waghmare +2
We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies t…
Appearance Consensus Driven Self-Supervised Human Mesh Recovery
Jogendra Nath Kundu, Mugalodi Rakesh, Varun Jampani +2
We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision. Recent advances have shifte…
Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Rahul M +3
Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose est…
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis
Jogendra Nath Kundu, Siddharth Seth, Varun Jampani +3
Camera captured human pose is an outcome of several sources of variation. Performance of supervised 3D pose estimation approaches comes at the cost of dispensing with variations, s…
Universal Source-Free Domain Adaptation
Jogendra Nath Kundu, Naveen Venkat, Rahul M +1
There is a strong incentive to develop versatile learning techniques that can transfer the knowledge of class-separability from a labeled source domain to an unlabeled target domai…
Towards Inheritable Models for Open-Set Domain Adaptation
Jogendra Nath Kundu, Naveen Venkat, Ambareesh Revanur +2
There has been a tremendous progress in Domain Adaptation (DA) for visual recognition tasks. Particularly, open-set DA has gained considerable attention wherein the target domain c…
GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions
Jogendra Nath Kundu, Maharshi Gor, Dakshit Agrawal +1
Despite the remarkable success of generative adversarial networks, their performance seems less impressive for diverse training sets, requiring learning of discontinuous mapping fu…