arXiv subjects

Gaurav Rai

Publications and source records attributed to Gaurav Rai.

5 recordsLinked to original sources

arXiv2026

TexSketch: Bringing Texture-Aware Colorization to Sketches

Reference-based sketch colorization methods rely on large paired datasets that preserve both the structural and stylistic characteristics of hand-drawn artwork. However, existing datasets are limited in scale, expensive to annotate, and bound to fixed, often inconsistent artistic style biases that propagate to downstream models and limit cross-domain generalization. We present TexSketch, a controllable procedural framework for generating colored-sketch datasets with programmable artistic styles via geometric analysis and shader-driven stylization. Our fully automatic pipeline integrates region extraction, semantic color prediction, and shader-based rendering. By defining artistic appearance procedurally rather than inheriting it from a static corpus, TexSketch enables scalable dataset generation without manual annotation or artist supervision. Human studies demonstrate that TexSketch generates perceptually plausible colored sketches with high stylistic diversity, providing a controllable, scalable source of synthetic supervision for sketch colorization.

cs.GR↗

arXiv2026

Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization

Animation of 2D hand-drawn sketches provides an effective medium for visual communication. However, these sketches pose challenges, particularly in handling occlusions and accurately mapping motion. While 3D animation naturally addresses these challenges, estimating 3D motion remains a very complex task. Recent approaches to converting 2D sketches to 3D animations have mainly focused on specific types of motion, such as bipedal movements and facial expressions. We propose Sketch2Motion, a diffusion-guided framework for skeleton-based motion synthesis that combines classical character animation pipelines with deep generative priors. Our method represents motion using skeletal transformations, which are propagated to mesh deformations via linear blend skinning. To guide the resulting animation toward realistic and semantically meaningful motion, we integrate a text-to-video diffusion model via motion-aware score-distillation sampling (MoSDS), enabling optimization without paired motion data. Additionally, we apply physics-inspired smoothness, topological, and contact constraints to stabilize optimization and preserve motion plausibility. Further, we integrate a spring-mass simulator to introduce secondary motion effects. The proposed framework is generalized, fully differentiable, modular, and compatible with biped, quadruped, and non-living articulated characters. Experiments demonstrate that our approach produces temporally coherent, text-aligned animations that outperform baseline motion transfer methods that lack generative priors or explicit physical constraints. We will make our code and dataset publicly available.

cs.CV↗

arXiv2025

Sketch Animation: State-of-the-art Report

Sketch animation has emerged as a transformative technology, bridging art and science to create dynamic visual narratives across various fields such as entertainment, education, healthcare, and virtual reality. This survey explores recent trends and innovations in sketch animation, with a focus on methods that have advanced the state of the art. The paper categorizes and evaluates key methodologies, including keyframe interpolation, physics-based animation, data-driven, motion capture, and deep learning approaches. We examine the integration of artificial intelligence, real-time rendering, and cloud-based solutions, highlighting their impact on enhancing realism, scalability, and interactivity. Additionally, the survey delves into the challenges of computational complexity, scalability, and user-friendly interfaces, as well as emerging opportunities within metaverse applications and human-machine interaction. By synthesizing insights from a wide array of research, this survey aims to provide a comprehensive understanding of the current landscape and future directions of sketch animation, serving as a resource for both academics and industry professionals seeking to innovate in this dynamic field.

cs.GR↗

arXiv2024

Enhancing Sketch Animation: Text-to-Video Diffusion Models with Temporal Consistency and Rigidity Constraints

Animating hand-drawn sketches using traditional tools is challenging and complex. Sketches provide a visual basis for explanations, and animating these sketches offers an experience of real-time scenarios. We propose an approach for animating a given input sketch based on a descriptive text prompt. Our method utilizes a parametric representation of the sketch's strokes. Unlike previous methods, which struggle to estimate smooth and accurate motion and often fail to preserve the sketch's topology, we leverage a pre-trained text-to-video diffusion model with SDS loss to guide the motion of the sketch's strokes. We introduce length-area (LA) regularization to ensure temporal consistency by accurately estimating the smooth displacement of control points across the frame sequence. Additionally, to preserve shape and avoid topology changes, we apply a shape-preserving As-Rigid-As-Possible (ARAP) loss to maintain sketch rigidity. Our method surpasses state-of-the-art performance in both quantitative and qualitative evaluations.

cs.CV↗

arXiv2021

Monitoring COVID-19 social distancing with person detection and tracking via fine-tuned YOLO v3 and Deepsort techniques

The rampant coronavirus disease 2019 (COVID-19) has brought global crisis with its deadly spread to more than 180 countries, and about 3,519,901 confirmed cases along with 247,630 deaths globally as on May 4, 2020. The absence of any active therapeutic agents and the lack of immunity against COVID-19 increases the vulnerability of the population. Since there are no vaccines available, social distancing is the only feasible approach to fight against this pandemic. Motivated by this notion, this article proposes a deep learning based framework for automating the task of monitoring social distancing using surveillance video. The proposed framework utilizes the YOLO v3 object detection model to segregate humans from the background and Deepsort approach to track the identified people with the help of bounding boxes and assigned IDs. The results of the YOLO v3 model are further compared with other popular state-of-the-art models, e.g. faster region-based CNN (convolution neural network) and single shot detector (SSD) in terms of mean average precision (mAP), frames per second (FPS) and loss values defined by object classification and localization. Later, the pairwise vectorized L2 norm is computed based on the three-dimensional feature space obtained by using the centroid coordinates and dimensions of the bounding box. The violation index term is proposed to quantize the non adoption of social distancing protocol. From the experimental analysis, it is observed that the YOLO v3 with Deepsort tracking scheme displayed best results with balanced mAP and FPS score to monitor the social distancing in real-time.

cs.CV↗