Searcharxiv⌕ Search

arXiv subjects

Trung-Nghia Le

Publications and source records attributed to Trung-Nghia Le.

At least 19 recordsLinked to original sources

CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation

Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items, and respecting a specified background scene, a regime where current diffusion models remain brittle. Existing benchmarks evaluate only one axis at a time and none jointly captures multi-identity composition with human-object interaction, background grounding, and spatial plausibility. We introduce CogCanvas, a benchmark of 1,952 curated reference images spanning 100 celebrity identities, 115 distinctive objects and fashion items, and 29 real-world background scenes including landmarks, from which we construct 1,361 compositional prompts covering 2-5 person group sizes. The curation pipeline combines DINOv2-based deduplication, two-stage aesthetic filtering, and automated derivation of structured interaction and position graphs that serve as ground-truth supervision. CogCanvas supports three tasks, reference-based multi-human-object generation (primary), text-to-image compositional generation, and reference retrieval, under a unified six-axis evaluation protocol. We introduce two metrics tailored to the multi-reference setting: BG-Sim, which scores background fidelity on SAM 3-masked regions via DINOv3 feature similarity, and Attr-VQA, which uses a multimodal LLM to verify per-subject attribute binding and inter-person interactions against the structured graphs. Benchmarking five SOTA methods reveals that every model degrades substantially as group size grows from 2 to 5, with near-complete failure on object/fashion binding beyond three subjects.

cs.CV↗

Content-Preserving Principal Feature Blending for Training-Free Style Personalization

Reference-based style personalization should reproduce the appearance of a style reference while preserving the subject specified by a content prompt. In visual autoregressive models, dominant reference features can also carry object and spatial information, causing content leakage. We propose Content-Preserving Principal Feature Blending (CoPFB), a training-free method that estimates a low-rank content basis from a clean generation branch and removes the content-aligned component of the style residual. CoPFB applies rank-one blending at the first two autoregressive scales, followed by weaker content-projected refinement at the next three scales. On 1,900 combinations of Parti content prompts and FineStyle reference images, CoPFB improves text alignment from 0.293 to 0.297 and the harmonic score from 0.391 to 0.393 over PFB+SAC, while style similarity decreases from 0.590 to 0.577. CoPFB requires no fine-tuning or learnable parameters.

cs.CV↗

NanoNet: Ultra-Lightweight Network for MRI Brain Tumor Classification toward Edge AI

Automated brain tumor classification from magnetic resonance imaging (MRI) can support accessible medical image analysis, but conventional deep learning models often exceed the resource budgets of highly constrained edge-AI platforms. We present NanoNet, an ultra-lightweight convolutional neural network designed for resourceconstrained MRI classification and motivated by future edge-AI applications. Inspired by MobileNetV2, NanoNet substantially reduces network depth, channel capacity, expansion ratios, and final feature dimensionality, resulting in only five inverted residual blocks and 8,132 parameters. We further investigate dependency-aware structured pruning, knowledge distillation, and INT8 quantization-aware training for additional compression. Experiments on the BRISC 2025 benchmark show that NanoNet achieves 92.80% accuracy and 92.97% macro F1 with 8,132 parameters and 10.498 MFLOPs. Across three compression seeds, it exceeds the mean accuracy of 70%-pruned MobileNetV2 by 5.20 percentage points while using 60.2% fewer parameters and 9.8% less computation. Converted INT8 NanoNet achieves 89.70% accuracy and 90.22% macro F1 across three QAT seeds. Earlier TensorFlow Lite measurements indicate 27.7 KB of baseline model storage, motivating future edge-AI deployment.

cs.CV↗

CounterSketch: Physics-Grounded Counterfactual Reasoning for Sketch-to-Video Generation

Counterfactual sketch animation explores how a static sketch evolves under a hypothetical intervention. We present CounterSketch, a physics-grounded framework that transforms natural-language ``What if...?'' queries into physically plausible sketch animations. The framework integrates VLM-guided scene grounding, causal event-chain reasoning, constraint-based trajectory generation, and verification. It models physical transitions to update the scene graph, computes continuous object trajectories, and validates them against physical, geometric, and semantic constraints. The verified trajectories are then projected into object-level motion bounding boxes to guide downstream sketch-video synthesis. Experiments on CounterSketchBench (80 questions) demonstrate that physics-grounded trajectories provide stronger motion guidance than direct VLM predictions.

cs.CV↗

OmniScribble: Mixed-Initiative Authoring of Animated Sketches through Inspectable and Repairable AI Decisions

AI-assisted creative tools reduce the effort of authoring content, but delegating creative decisions to AI can make it difficult for authors to understand, correct, or redirect work. We present OmniScribble, a system for animating multi-object sketches that treats object decomposition and motion planning as editable artifacts. Rather than generating animation end-to-end, OmniScribble presents AI proposals at verification checkpoints, where authors can accept, repair, or regenerate them. Both manual and AI-assisted authoring operate on the intermediate representation and rendering pipeline, allowing us to isolate AI delegation. In a within-subject study with eight participants, AI-assisted authoring yielded a median within-participant reduction in completion time of 71.4\%, while perceived control and motion-intent alignment remained high. Interaction traces and interviews show that participants adapted to AI errors by repairing local issues, regenerating mismatches, and accepting proposals. These findings suggest that inspectable, repairable delegation enables generative automation while maintaining control over the outcome.

cs.HC↗

GEAR: Generative Editing for Scene-Conditioned Outfit Retrieval for VR Travel

In virtual environments, choosing appropriate outfits requires contextual harmony with surrounding scenes, yet bridging the visual gap between 3D ambient views and catalog garment assets remains challenging. This paper investigates scene-conditioned outfit retrieval for interactive 3D environments, where a user's egocentric view serves as the retrieval signal. We present GEAR (Generative Editing for Asset Retrieval), a framework that bridges the cross-domain gap by synthesizing intermediate visual queries rather than predicting direct compatibility. GEAR uses a vision-language model to describe suitable clothing from a captured scene, employs an instruction-guided diffusion model to render the concept onto a standardized reference character, and utilizes the cropped clothing region to retrieve existing 2D outfit assets via embedding similarity. An interactive Unity prototype demonstrates real-time scene capture, asset retrieval, and in-engine 3D avatar fitting. We benchmark GEAR against direct visual similarity, aesthetic scoring, and VLM-based reranking on a controlled dataset using automated Swiss-system pairwise judgments, where GEAR achieves competitive top-ranked performance (mean Elo@5 of 1012.75 and top-10 overlap of 0.180) alongside 0.539 pairwise agreement. Furthermore, a user study across 20 virtual travel scenes demonstrates that GEAR achieves the highest overall participant preference in both visual appeal (34.5%) and contextual suitability (34.5%).

cs.CV↗

Density-Aware Calibration for Resource-Efficient Medical Vision-Language Models

Medical vision-language models (VLMs) show promise for clinical image understanding, but their computational and memory requirements hinder deployment on resource-constrained clinical hardware. Post-training quantization (PTQ) offers a practical compression strategy without retraining, yet its effectiveness depends strongly on the calibration data. We propose CoreCalib, a training-free and quantizer-agnostic framework for constructing compact calibration sets that preserve the target medical VQA distribution. CoreCalib stratifies data by clinical question class, identifies representative visual modes using frozen DINOv2 features with UMAP and HDBSCAN, and expands selected images into class-balanced question-answer pairs. On Kvasir-VQA-x1, we evaluate CoreCalib with MASQuant, GPTQ, and QIG using a fixed 128-pair budget. CoreCalib achieves the best METEOR with all three quantizers and the best ROUGE-L with MASQuant and GPTQ. With W4A8 MASQuant, it improves METEOR from 0.5672 with COCO calibration to 0.6234, recovering approximately 41% of the degradation relative to BF16. These results support CoreCalib as a data-centric component for resource-efficient medical VLM deployment. Project page: https://magnusdtd.github.io/CoreCalib/ .

cs.CV↗

SAVIER: Source-Anchored Visual Inspection and Evidence-Guided Repair for Vietnamese Cultural Text-to-Image Generation

We present SAVIER, a training-free, one-pass framework that repairs the depiction of a named Vietnamese cultural entity in a generated image while preserving the scene details requested by the user. The problem is hard because a plausible scene can miss the cues that identify the entity, and prompt-level refinement never inspects the image it produces. SAVIER starts from a Culture-TRIP expanded prompt; a Curator separates source-linked cultural cues from prompt-preservation requirements, a prompt-blind Observer describes the first image, and a Refiner turns the discrepancies into at most three positive instructions before one regeneration with the same seed and a fixed bank of reference photographs. On the 50 bilingual prompts of ViCuP, evaluated with SDXL and FLUX.1-dev against a frozen, human-verified visual contract, SAVIER raises contract fulfillment from 55.6 to 69.6 and from 59.1 to 67.3 over Culture-TRIP and raises CAIRE cultural relevance on FLUX.1-dev. A reference-only ablation that removes the agent repair shows that SAVIER's photographs account for most of the contract gain; the agent roles add country-level relevance on FLUX.1-dev without lowering adherence to the original prompt under the official VQAScore. Project page: https://oxyzgiahuy.github.io/savier/

cs.CV↗

Directional Dual-Head Supervision for Real-Time Source-Free Polyp Segmentation

Source-free domain adaptation (SFDA) is critical for medical image segmentation as it adapts a model to an unlabeled target domain without accessing source data, thereby preserving data privacy. However, its effectiveness is often limited by confirmation bias: self-training models tend to miss small polyps, hallucinate foreground, and produce imprecise contours. We propose MedRT-SFSeg, a real-time SFDA framework built on a dual-head one-to-one/one-to-many YOLO segmentation architecture. Mask-DHF fuses precision- and recall-oriented predictions into stable pseudo-instances, while DURR uses the sign of pixel-level dual-head disagreement as a directional cue to expand or shrink masks, and additionally recovers missed instances and suppresses hallucinations. Seg-MARD further regularizes feature representations through mask-guided, region-stratified sampling. Experiments on bidirectional adaptation between Kvasir-SEG and CVC-ClinicDB show that MedRT-SFSeg achieves 80.43%/80.77% Dice and 5.53/8.44 mm ASD, improving the non-adapted baseline by 7.7 and 9.8 Dice points while running at more than 62 FPS end-to-end. These results suggest that segmentation-aware dual-head supervision can improve pseudo-label quality without sacrificing real-time inference. Project page: https://danielnguyen-05.github.io/MedRT-SFSeg

eess.IV↗

SketchBloom: Training-Free Vector Sketch Outpainting with Stroke-Level Style Control

Outpainting sparse sketches while preserving contour coherence and stroke style remains challenging. We present SketchBloom, a training-free framework that combines pretrained raster outpainting and style-transfer guidance with per-instance vector optimization. Given a sketch, a scene prompt, and an optional reference style, it produces an editable Scalable Vector Graphic (SVG) composed of Bezier strokes. Adaptive latent blending balances content contours and reference texture without model retraining. A reference-derived stroke vocabulary initializes contour- and DINO-attention-guided strokes, which are optimized separately for structure and texture before contour-emphasizing multiply fusion. As in prior optimization-based vector sketching, no task-specific network is trained; our contribution is the synthesis design specialized to sketch outpainting. On LineArtOut-1K, comprising 1,024 input and style combinations, SketchBloom improves perceptual, semantic, and structural fidelity over the evaluated vector baselines when all methods vectorize the same outpainted raster. This protocol evaluates vector synthesis rather than end-to-end outpainting or reference-style superiority. Runtime is approximately six minutes per pair on a single NVIDIA H200 GPU. Project page: https://khangcntn123.github.io/SketchBloom/

cs.CV↗

SketchForge: Training-Free Scene-to-Vector Sketching via Decoupled Structure and Texture Optimization

Converting a raster image into a resolution-independent, stroke-editable vector sketch while faithfully preserving both structural contours and tonal texture remains challenging: raster-space rendering pipelines are difficult to edit at the stroke level, while generation-from-scratch vectorization methods struggle to remain faithful to an arbitrary input image. We present SketchForge, a training-free framework that converts an input raster image into a resolution-independent SVG sketch through per-instance test-time optimization of Bezier curves, requiring no additional training or fine-tuning. Strokes are seeded via a contour and attention-guided initialization, then refined by a vector-native differentiable rendering pipeline that decouples structural contour strokes from free-form texture strokes under dedicated objectives, composited via multiply-blend layering. Extensive experiments show that SketchForge consistently outperforms existing vector-based baselines in structural fidelity and generation quality. Project page: https://khangcntn123.github.io/SketchForge

cs.CV↗

Kingfisher: Fast Personalized Visual Autoregressive Generation via Scale-Aware Prompt-Conditioned Scale Decomposition

Personalized image generation has been extensively studied in diffusion models, often relying on subject-specific optimization of model weights, textual embeddings, LoRA modules, or adapters. In this work, we explore a different direction for fast personalization in visual autoregressive models. Our key observation is that a short prefix of early autoregressive scale codes is sufficient to strongly determine both object structure and global appearance, while later scales primarily refine the established generation trajectory. Based on this insight, we introduce Kingfisher, a model-tuning-free framework that decomposes early residual scale codes into content- and style-related components through prompt-conditioned scale-code subspaces. Given two real images, Kingfisher first decomposes their early scale codes, then recomposes the content components of one image with the style components of the other into a compact semantic prefix. The frozen generator subsequently predicts the remaining scales through bitwise self-correction for coherent refinement. Experiments on CSD-100 show that Kingfisher achieves strong content preservation and the highest style and text alignment among the evaluated methods, while reducing pair-specific preparation time by approximately 54x compared with diffusion-based methods and 7.5x compared with VAR-based alternatives. These results demonstrate that effective personalization can be achieved by directly manipulating the native scale-space representation of a frozen visual autoregressive generator.

cs.CV↗

PhysMirror: Physics-Aware Mirror Object Generation

Synthesizing physically accurate mirror reflections remains a fundamental challenge for modern text-to-image diffusion models, which are increasingly critical for generating synthetic training data for embodied AI and robotic perception. These models typically struggle with strict geometric constraints, leading to hallucinations that degrade the utility of the synthetic data. To address this, we introduce a novel, end-to-end physics-aware generation framework namely PhysMirror that natively enforces projective geometry through explicit 3D spatial priors. Our method automatically lifts prompted objects into 3D meshes and constructs a lightweight, mathematically exact mirror scene within a simulated environment. By rendering this explicit 3D scene, we extract precise 2D conditioning elements, such as depth maps and segmentation maps, that serve as robust guiding signals for downstream diffusion models, guiding them to generate images with physically correct mirror reflections. Moreover, we introduce Mirror Consistency Score (MCS), reference-free, fully automated metric that quantifies physical correctness using dense feature matching and vanishing point convergence. Experimental results on our newly constructed MirrOB dataset demonstrate that our approach outperforms state-of-the-art baselines in reflection accuracy and physical realism, while maintaining strong text-to-image semantic alignment, providing a reliable pipeline for embodied AI data generation. The source code is released at https://duyphuc0701.github.io/PhysMirror.

cs.CV↗

PhysPlan: Grounded Physical State Reasoning and Graph-Guided Optimization for Physically Plausible Video Generation

Video diffusion models (VDMs) synthesize photorealistic content, yet they often fail to follow the course that a physical phenomenon should take within a given scene. Recent training-free methods let a vision-language model (VLM) plan the phenomenon and guide a frozen VDM toward the plan; however, such plans are derived from the prompt and consumed as whole keyframes or trajectories, which leaves unspecified where the consequences land in the observed scene and turns incidental visual details into optimization targets. We observe that a phenomenon specified in words unfolds as sparse, local changes to the physical state of the observed scene. Building on this observation, we present PhysPlan, a training-free image-to-video framework that represents a phenomenon as a grounded state graph and uses this graph to decide what, where, and when the guidance constrains. Grounded Physical State Reasoning decomposes the phenomenon into physical deltas, each stating which objects change, to what state, and by which physical rule, and translates each delta into graph edits, verified by deterministic checks, that leave all other objects unchanged. Graph-Guided Test-Time Optimization renders a keyframe for each state, measures the denoised estimates only along the properties selected by the edits, and concentrates the update on the edited objects. On PhyGenBench and Physics-IQ, PhysPlan raises its base model from 0.52 to 0.77 and from 27.1 to 38.2, surpassing the strongest prior I2V method (0.60 and 34.6), and lowers FVD by over 20%. Project page: https://physplan.github.io

cs.CV↗

ViFA-Council: Multi-Agent LLM Deliberation for Vietnamese Folk Art Generation

This paper presents ViFA-Council, a three-stage multi-agent framework that employs multiple large language models (LLMs) to tackle two culturally complex generative tasks: image outpainting and educational story generation based on traditional Vietnamese folk paintings. Current single-model generative pipelines frequently struggle with stylistic hallucinations and cultural misrepresentations because they lack mechanisms for cross-model critique. ViFA-Council addresses this challenge by orchestrating collaboration among GPT-4o, Gemini 3.1 Pro, and Claude Sonnet 4.6. It enforces rigorous cultural constraints through structured agent deliberation. This deliberation is mediated by task-specific JSON schemas that effectively bridge natural language discussions with diffusion-based image synthesis using Banana Pro. Experiments and a user study demonstrate that structured multi-agent deliberation is a promising direction for improving cultural fidelity and narrative coherence in culturally sensitive, low-resource artistic domains. The source code and data are released at https://github.com/DanielNguyen-05/ViFA-Council.

cs.GR↗

Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification

In chest X-ray (CXR) classification, acceptable ranking performance can still leave rare-positive patients below threshold, especially within subgroups. We study this pre-deployment fairness problem as an audit question: after a long-tailed multi-label CXR model is converted from scores into decisions, who is missed? Across VinDr-CXR and MIMIC-CXR/CXR-LT, we use a diagnostic ladder to separate class-level long-tail losses, subgroup-aware weighting, group robustness, and threshold selection. On VinDr-CXR, group-tail weighting followed by tail-aware thresholding reduces tail FNR from 0.665 to 0.269, sex worst-group FNR from 0.705 to 0.157, and age worst-group FNR from 0.822 to 0.133, while macro-mAP increases from 0.611 to 0.635. On MIMIC-CXR/CXR-LT, the same score-to-threshold comparison reduces tail FNR from 0.866 to 0.741 and lowers worst-group FNR across sex, age, race, and insurance; residual missed-positive rates nevertheless remain high. Paired bootstrap contrasts on VinDr support the thresholded FNR reductions, and GroupDRO reference runs indicate that aggregate group robustness alone does not remove rare subgroup misses in this setting. The study supports a narrow audit claim: rare-label fairness in CXR depends jointly on the finding, subgroup, and operating threshold, not on label frequency or ranking metrics alone.

cs.LG↗

Learning to Generate Multiple Objects from Dense and Occluded Layouts

Text-to-image diffusion models fail to generate correct object counts in dense scenes, where overlapping instances collapse into indistinguishable structures despite appearing visually plausible. We identify this as instance ownership collapse: tokens from overlapping objects interact freely through attention, while heavily occluded instances receive weak supervision due to their small visible areas. We address this through layout-aware attention biases that softly bias token interactions toward region-consistent grouping and suppress cross-instance leakage, paired with an amodal-balanced loss that amplifies gradients for occluded objects based on their occlusion level. To enable systematic evaluation, we introduce OverlapDepth-45K, a benchmark of densely overlapping scenes with amodal supervision. Our approach substantially improves count accuracy and prevents instance merging while preserving image quality. Project page: https://bachngoh.github.io/AIBL

cs.CV↗

AI-Generated Image Recognition via Fusion of CNNs and Vision Transformers

Recent advancements in synthetic data technology have opened a new era where images of remarkable quality are generated, blurring the lines between real-life images and those produced by Artificial Intelligence (AI). This evolution poses a significant challenge to ensuring the reliability and authenticity of data, underscoring the need for robust detection methods. In this paper, we present a robust approach aimed at addressing these pressing concerns. Our methodology revolves around leveraging fusion strategies, combining the strengths of multiple detection methods for identifying AI-generated images. Through extensive experimentation on the CIFAKE dataset, our model showcases remarkable performance, achieving an impressive accuracy rate of 97.32%. This accomplishment underscores the efficacy of our approach in accurately distinguishing between AI-generated images and real-life images, thus contributing to the advancement of data authentication techniques amidst the proliferation of synthetic data.

cs.CV↗