arXiv subjects

Hrishav Bakul Barua

Publications and source records attributed to Hrishav Bakul Barua.

At least 19 recordsLinked to original sources

arXiv2026

RAPiD: Reward-Guided Consistency Distillation of Diffusion Planners for Real-Time Autonomous Driving

Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment. We present RAPiD, a reward-guided consistency distillation framework that distills a pretrained DiffusionPlanner into a few-step consistency student while retaining multi-modal trajectory generation. The student is trained using deterministic teacher denoising steps from the frozen diffusion planner, together with a low-noise data anchor that keeps generated trajectories grounded in expert demonstrations. To make distillation safety-aware, we train an Implicit Q-Learning critic on a balanced mixture of ground-truth log-replay and DiffusionPlanner rollout trajectories, each scored using a modified PDM-style reward, providing trajectory-level supervision beyond conventional imitation learning. During deployment, the 2-step student generates K trajectories, and the trained critic performs best-of-K trajectory selection conditioned on the latent state. On nuPlan, RAPiD maintains comparable performance to the diffusion teacher on non-reactive closed-loop splits and remains competitive on reactive splits, while reducing complete-pipeline inference latency from 100.91 ms to 18.41 ms, corresponding to a 5.5x speedup. On interPlan, RAPiD achieves the highest aggregate score among learning-based methods, demonstrating competitive generalization in interactive long-tail scenarios. These results show that reward-guided consistency distillation can convert a pretrained diffusion planner into a few-step closed-loop planner that substantially reduces inference cost while preserving safety-oriented trajectory selection. The official website of this work is: https://github.com/ruturajreddy/RAPiD

cs.AI↗

arXiv2026

Seeing Roads Through Words: A Language-Guided Framework for RGB-T Driving Scene Segmentation

Robust semantic segmentation of road scenes under adverse illumination, lighting, and shadow conditions remain a core challenge for autonomous driving applications. RGB-Thermal fusion is a standard approach, yet existing methods apply static fusion strategies uniformly across all conditions, allowing modality-specific noise to propagate throughout the network. Hence, we propose CLARITY that dynamically adapts its fusion strategy to the detected scene condition. Guided by vision-language model (VLM) priors, the network learns to modulate each modality's contribution based on the illumination state while leveraging object embeddings for segmentation, rather than applying a fixed fusion policy. We further introduce two mechanisms - one which preserves valid dark-object semantics that prior noise-suppression methods incorrectly discard, and a hierarchical decoder that enforces structural consistency across scales to sharpen boundaries on thin objects. Experiments on the MFNet dataset demonstrate that CLARITY establishes a new state-of-the-art (SOTA), achieving 62.3% mIoU and 77.5% mAcc.

cs.CV↗

arXiv2025

DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors

The trend in sign language generation is centered around data-driven generative methods that require vast amounts of precise 2D and 3D human pose data to achieve an acceptable generation quality. However, currently, most sign language datasets are video-based and limited to automatically reconstructed 2D human poses (i.e., keypoints) and lack accurate 3D information. Furthermore, existing state-of-the-art for automatic 3D human pose estimation from sign language videos is prone to self-occlusion, noise, and motion blur effects, resulting in poor reconstruction quality. In response to this, we introduce DexAvatar, a novel framework to reconstruct bio-mechanically accurate fine-grained hand articulations and body movements from in-the-wild monocular sign language videos, guided by learned 3D hand and body priors. DexAvatar achieves strong performance in the SGNify motion capture dataset, the only benchmark available for this task, reaching an improvement of 35.11% in the estimation of body and hand poses compared to the state-of-the-art. The official website of this work is: https://github.com/kaustesseract/DexAvatar.

cs.CV↗

arXiv2025

A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction

Reconstruction of High Dynamic Range (HDR) from Low Dynamic Range (LDR) images is an important computer vision task. There is a significant amount of research utilizing both conventional non-learning methods and modern data-driven approaches, focusing on using both single-exposed and multi-exposed LDR for HDR image reconstruction. However, most current state-of-the-art methods require high-quality paired {LDR;HDR} datasets with limited literature use of unpaired datasets, that is, methods that learn the LDR-HDR mapping between domains. This paper proposes CycleHDR, a method that integrates self-supervision into a modified semantic- and cycle-consistent adversarial architecture that utilizes unpaired LDR and HDR datasets for training. Our method introduces novel artifact- and exposure-aware generators to address visual artifact removal. It also puts forward an encoder and loss to address semantic consistency, another under-explored topic. CycleHDR is the first to use semantic and contextual awareness for the LDR-HDR reconstruction task in a self-supervised setup. The method achieves state-of-the-art performance across several benchmark datasets and reconstructs high-quality HDR images. The official website of this work is available at: https://github.com/HrishavBakulBarua/Cycle-HDR

cs.CV↗

arXiv2025

Seeing in the Dark: A Teacher-Student Framework for Dark Video Action Recognition via Knowledge Distillation and Contrastive Learning

Action recognition in dark or low-light (under-exposed) videos is a challenging task due to visibility degradation, which can hinder critical spatiotemporal details. This paper proposes ActLumos, a teacher-student framework that attains single-stream inference while retaining multi-stream level accuracy. The teacher consumes dual stream inputs, which include original dark frames and retinex-enhanced frames, processed by weight-shared R(2+1)D-34 backbones and fused by a Dynamic Feature Fusion (DFF) module, which dynamically re-weights the two streams at each time step, emphasising the most informative temporal segments. The teacher is also included with a supervised contrastive loss (SupCon) that sharpens class margins. The student shares the R(2+1)D-34 backbone but uses only dark frames and no fusion at test time. The student is first pre-trained with self-supervision on dark clips of both datasets without their labels and then fine-tuned with knowledge distillation from the teacher, transferring the teacher's multi-stream knowledge into a single-stream model. Under single-stream inference, the distilled student attains state-of-the-art accuracy of 96.92% (Top-1) on ARID V1.0, 88.27% on ARID V1.5, and 48.96% on Dark48. Ablation studies further highlight the individual contributions of each component, i.e., DFF in the teacher outperforms single or static fusion, knowledge distillation (KD) transfers these gains to the single-stream student, and two-view spatio-temporal SSL surpasses spatial-only or temporal-only variants without increasing inference cost. The official website of this work is available at: https://github.com/HrishavBakulBarua/ActLumos

cs.CV↗

arXiv2025

PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction

Low Dynamic Range (LDR) to High Dynamic Range (HDR) image translation is a fundamental task in many computational vision problems. Numerous data-driven methods have been proposed to address this problem; however, they lack explicit modeling of illumination, lighting, and scene geometry in images. This limits the quality of the reconstructed HDR images. Since lighting and shadows interact differently with different materials, (e.g., specular surfaces such as glass and metal, and lambertian or diffuse surfaces such as wood and stone), modeling material-specific properties (e.g., specular and diffuse reflectance) has the potential to improve the quality of HDR image reconstruction. This paper presents PhysHDR, a simple yet powerful latent diffusion-based generative model for HDR image reconstruction. The denoising process is conditioned on lighting and depth information and guided by a novel loss to incorporate material properties of surfaces in the scene. The experimental results establish the efficacy of PhysHDR in comparison to a number of recent state-of-the-art methods.

cs.GR↗

arXiv2024

Demystifying Object-based Big Data Storage Systems

Today's era is the digitized era. Managing such generated big data is an important factor for data scientists. Day by day, it increases the demand for big data storage systems. Different organizations are involved in providing storage-related services. They follow the different architectures or storage models for storing big data. In this survey paper, our target is to highlight such storage architectures which provided by different renowned storage service providers. On an architectural basis, we divide the big data storage systems into five parts, Distributed file systems (DFS), Clustered File Systems (CFS), Cloud Storage, Archive Storage, and Object Storage Systems (OSS). Also, we reveal a detailed architectural view of the big data storage systems provided by the different organizations under these parts.

cs.DB↗

arXiv2024

ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos

Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot interaction and many more. Traditional supervised methods require large annotated datasets for training, which are expensive and time-consuming to acquire. This work proposes a novel approach using Cross-Architecture Pseudo-Labeling with contrastive learning for semi-supervised action recognition. Our framework leverages both labeled and unlabelled data to robustly learn action representations in videos, combining pseudo-labeling with contrastive learning for effective learning from both types of samples. We introduce a novel cross-architecture approach where 3D Convolutional Neural Networks (3D CNNs) and video transformers (VIT) are utilised to capture different aspects of action representations; hence we call it ActNetFormer. The 3D CNNs excel at capturing spatial features and local dependencies in the temporal domain, while VIT excels at capturing long-range dependencies across frames. By integrating these complementary architectures within the ActNetFormer framework, our approach can effectively capture both local and global contextual information of an action. This comprehensive representation learning enables the model to achieve better performance in semi-supervised action recognition tasks by leveraging the strengths of each of these architectures. Experimental results on standard action recognition datasets demonstrate that our approach performs better than the existing methods, achieving state-of-the-art performance with only a fraction of labeled data. The official website of this work is available at: https://github.com/rana2149/ActNetFormer.

cs.CV↗

arXiv2024

GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction

High Dynamic Range (HDR) content (i.e., images and videos) has a broad range of applications. However, capturing HDR content from real-world scenes is expensive and time-consuming. Therefore, the challenging task of reconstructing visually accurate HDR images from their Low Dynamic Range (LDR) counterparts is gaining attention in the vision research community. A major challenge in this research problem is the lack of datasets, which capture diverse scene conditions (e.g., lighting, shadows, weather, locations, landscapes, objects, humans, buildings) and various image features (e.g., color, contrast, saturation, hue, luminance, brightness, radiance). To address this gap, in this paper, we introduce GTA-HDR, a large-scale synthetic dataset of photo-realistic HDR images sampled from the GTA-V video game. We perform thorough evaluation of the proposed dataset, which demonstrates significant qualitative and quantitative improvements of the state-of-the-art HDR image reconstruction methods. Furthermore, we demonstrate the effectiveness of the proposed dataset and its impact on additional computer vision tasks including 3D human pose estimation, human body part segmentation, and holistic scene segmentation. The dataset, data collection pipeline, and evaluation code are available at: https://github.com/HrishavBakulBarua/GTA-HDR.

cs.CV↗

arXiv2024

HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translation

High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. Due to the high costs associated with HDR imaging, the literature offers various data-driven methods for HDR image reconstruction from Low Dynamic Range (LDR) counterparts. A common limitation of these approaches is missing details in regions of the reconstructed HDR images, which are over- or under-exposed in the input LDR images. To this end, we propose a simple and effective method, HistoHDR-Net, to recover the fine details (e.g., color, contrast, saturation, and brightness) of HDR images via a fusion-based approach utilizing histogram-equalized LDR images along with self-attention guidance. Our experiments demonstrate the efficacy of the proposed approach over the state-of-art methods.

eess.IV↗

arXiv2023

ArtHDR-Net: Perceptually Realistic and Accurate HDR Content Creation

High Dynamic Range (HDR) content creation has become an important topic for modern media and entertainment sectors, gaming and Augmented/Virtual Reality industries. Many methods have been proposed to recreate the HDR counterparts of input Low Dynamic Range (LDR) images/videos given a single exposure or multi-exposure LDRs. The state-of-the-art methods focus primarily on the preservation of the reconstruction's structural similarity and the pixel-wise accuracy. However, these conventional approaches do not emphasize preserving the artistic intent of the images in terms of human visual perception, which is an essential element in media, entertainment and gaming. In this paper, we attempt to study and fill this gap. We propose an architecture called ArtHDR-Net based on a Convolutional Neural Network that uses multi-exposed LDR features as input. Experimental results show that ArtHDR-Net can achieve state-of-the-art performance in terms of the HDR-VDP-2 score (i.e., mean opinion score index) while reaching competitive performance in terms of PSNR and SSIM.

cs.CV↗

arXiv2023

Computational Solar Energy -- Ensemble Learning Methods for Prediction of Solar Power Generation based on Meteorological Parameters in Eastern India

The challenges in applications of solar energy lies in its intermittency and dependency on meteorological parameters such as; solar radiation, ambient temperature, rainfall, wind-speed etc., and many other physical parameters like dust accumulation etc. Hence, it is important to estimate the amount of solar photovoltaic (PV) power generation for a specific geographical location. Machine learning (ML) models have gained importance and are widely used for prediction of solar power plant performance. In this paper, the impact of weather parameters on solar PV power generation is estimated by several Ensemble ML (EML) models like Bagging, Boosting, Stacking, and Voting for the first time. The performance of chosen ML algorithms is validated by field dataset of a 10kWp solar PV power plant in Eastern India region. Furthermore, a complete test-bed framework has been designed for data mining as well as to select appropriate learning models. It also supports feature selection and reduction for dataset to reduce space and time complexity of the learning models. The results demonstrate greater prediction accuracy of around 96% for Stacking and Voting EML models. The proposed work is a generalized one and can be very useful for predicting the performance of large-scale solar PV power plants also.

cs.LG↗

arXiv2022

VacciNet: Towards a Smart Framework for Learning the Distribution Chain Optimization of Vaccines for a Pandemic

Vaccinations against viruses have always been the need of the hour since long past. However, it is hard to efficiently distribute the vaccines (on time) to all the corners of a country, especially during a pandemic. Considering the vastness of the population, diversified communities, and demands of a smart society, it is an important task to optimize the vaccine distribution strategy in any country/state effectively. Although there is a profusion of data (Big Data) from various vaccine administration sites that can be mined to gain valuable insights about mass vaccination drives, very few attempts has been made towards revolutionizing the traditional mass vaccination campaigns to mitigate the socio-economic crises of pandemic afflicted countries. In this paper, we bridge this gap in studies and experimentation. We collect daily vaccination data which is publicly available and carefully analyze it to generate meaning-full insights and predictions. We put forward a novel framework leveraging Supervised Learning and Reinforcement Learning (RL) which we call VacciNet, that is capable of learning to predict the demand of vaccination in a state of a country as well as suggest optimal vaccine allocation in the state for minimum cost of procurement and supply. At the present, our framework is trained and tested with vaccination data of the USA.

cs.LG↗

arXiv2022

A Perspective on Robotic Telepresence and Teleoperation using Cognition: Are we there yet?

Telepresence and teleoperation robotics have attracted a great amount of attention in the last 10 years. With the Artificial Intelligence (AI) revolution already being started, we can see a wide range of robotic applications being realized. Intelligent robotic systems are being deployed both in industrial and domestic environments. Telepresence is the idea of being present in a remote location virtually or via robotic avatars. Similarly, the idea of operating a robot from a remote location for various tasks is called teleoperation. These technologies find significant application in health care, education, surveillance, disaster recovery, and corporate/government sectors. But question still remains about their maturity, security and safety levels. We also need to think about enhancing the user experience and trust in such technologies going into the next generation of computing.

cs.RO↗

arXiv2021

Detecting socially interacting groups using f-formation: A survey of taxonomy, methods, datasets, applications, challenges, and future research directions

Robots in our daily surroundings are increasing day by day. Their usability and acceptability largely depend on their explicit and implicit interaction capability with fellow human beings. As a result, social behavior is one of the most sought-after qualities that a robot can possess. However, there is no specific aspect and/or feature that defines socially acceptable behavior and it largely depends on the situation, application, and society. In this article, we investigate one such social behavior for collocated robots. Imagine a group of people is interacting with each other and we want to join the group. We as human beings do it in a socially acceptable manner, i.e., within the group, we do position ourselves in such a way that we can participate in the group activity without disturbing/obstructing anybody. To possess such a quality, first, a robot needs to determine the formation of the group and then determine a position for itself, which we humans do implicitly. The theory of f-formation can be utilized for this purpose. As the types of formations can be very diverse, detecting the social groups is not a trivial task. In this article, we provide a comprehensive survey of the existing work on social interaction and group detection using f-formation for robotics and other applications. We also put forward a novel holistic survey framework combining all the possible concerns and modules relevant to this problem. We define taxonomies based on methods, camera views, datasets, detection capabilities and scale, evaluation approaches, and application areas. We discuss certain open challenges and limitations in current literature along with possible future research directions based on this framework. In particular, we discuss the existing methods/techniques and their relative merits and demerits, applications, and provide a set of unsolved but relevant problems in this domain.

cs.AI↗

arXiv2021

Data science and Machine learning in the Clouds: A Perspective for the Future

As we are fast approaching the beginning of a paradigm shift in the field of science, Data driven science (the so called fourth science paradigm) is going to be the driving force in research and innovation. From medicine to biodiversity and astronomy to geology, all these terms are somehow going to be affected by this paradigm shift. The huge amount of data to be processed under this new paradigm will be a major concern in the future and one will strongly require cloud based services in all the aspects of these computations (from storage to compute and other services). Another aspect will be energy consumption and performance of prediction jobs and tasks within such a scientific paradigm which will change the way one sees computation. Data science has heavily impacted or rather triggered the emergence of Machine Learning, Signal/Image/Video processing related algorithms, Artificial intelligence, Robotics, health informatics, geoinformatics, and many more such areas of interest. Hence, we envisage an era where Data science can deliver its promises with the help of the existing cloud based platforms and services with the addition of new services. In this article, we discuss about data driven science and Machine learning and how they are going to be linked through cloud based services in the future. It also discusses the rise of paradigms like approximate computing, quantum computing and many more in recent times and their applicability in big data processing, data science, analytics, prediction and machine learning in the cloud environments.

cs.DC↗

arXiv2021

Approximate Computing for Robotic path planning -- Experimentation, Case Study and Practical Implications

Approximate computing is a computation domain which can be used to trade time and energy with quality and therefore is useful in embedded systems. Energy is the prime resource in battery-driven embedded systems, like robots. Approximate computing can be used as a technique to generate approximate version of the control functionalities of a robot, enabling it to ration energy for computation at the cost of degraded quality. Usually, the programmer of the function specifies the extent of degradation that is safe for the overall safety of the system. However, in a collaborative environment, where several sub-systems co-exist and some of the functionality of each of them have been approximated, the safety of the overall system may be compromised. In this paper, we consider multiple identical robots operate in a warehouse, and the path planning function of the robot is approximated. Although the planned paths are safe for individual robots (i.e. they do not collide with the racks), we show that this leads to a collision among the robots. So, a controlled approximation needs to be carried out in such situations to harness the full power of this new paradigm if it needs to be a mainstream paradigm in future.

cs.RO↗

arXiv2021

Cloud Big Data Mining and Analytics: Bringing Greenness and Acceleration in the Cloud

Big data is gaining overwhelming attention since the last decade. Almost all the fields of science and technology have experienced a considerable impact from it. The cloud computing paradigm has been targeted for big data processing and mining in a more efficient manner using the plethora of resources available from computing nodes to efficient storage. Cloud data mining introduces the concept of performing data mining and analytics of huge data in the cloud availing the cloud resources. But can we do better? Yes, of course! The main contribution of this chapter is the identification of four game-changing technologies for the acceleration of computing and analysis of data mining tasks in the cloud. Graphics Processing Units can be used to further accelerate the mining or analytic process, which is called GPU accelerated analytics. Further, Approximate Computing can also be introduced in big data analytics for bringing efficacy in the process by reducing time and energy and hence facilitating greenness in the entire computing process. Quantum Computing is a paradigm that is gaining pace in recent times which can also facilitate efficient and fast big data analytics in very little time. We have surveyed these three technologies and established their importance in big data mining with a holistic architecture by combining these three game-changers with the perspective of big data. We have also talked about another future technology, i.e., Neural Processing Units or Neural accelerators for researchers to explore the possibilities. A brief explanation of big data and cloud data mining concepts are also presented here.

cs.DC↗