arXiv subjects

Tae-Hyun Oh

Publications and source records attributed to Tae-Hyun Oh.

At least 37 records · Page 2Linked to original sources

arXiv2026

Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow

Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the correct image region corresponding to the question, they do not necessarily produce the correct answers. In this work, we demonstrate that this misalignment could be attributed to suboptimal information flow within VLMs, where text tokens distribute too much attention to irrelevant visual tokens, leading to incorrect answers. Based on the observation, we show that modulating the information flow during inference can improve the perception capability of VLMs. The idea is that text tokens should only be associated with important visual tokens during decoding, eliminating the interference of irrelevant regions. To achieve this, we propose a token dynamics-based method to determine the importance of visual tokens, where visual tokens that exhibit distinct activation patterns during different decoding stages are viewed as important. We apply our approach to representative open-source VLMs and evaluate on various datasets, including visual question answering, visual grounding and counting, optical character recognition, and object hallucination. The results show that our approach significantly improves the performance of baselines. Project page: https://cxliu0.github.io/AIF/.

cs.CV↗

arXiv2026

Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices

We introduce Fact-Hash, a novel parameter-encoding method for training on-device neural radiance fields. Neural Radiance Fields (NeRF) have proven pivotal in 3D representations, but their applications are limited due to large computational resources. On-device training can open large application fields, providing strength in communication limitations, privacy concerns, and fast adaptation to a frequently changing scene. However, challenges such as limited resources (GPU memory, storage, and power) impede their deployment. To handle this, we introduce Fact-Hash, a novel parameter-encoding merging Tensor Factorization and Hash-encoding techniques. This integration offers two benefits: the use of rich high-resolution features and the few-shot robustness. In Fact-Hash, we project 3D coordinates into multiple lower-dimensional forms (2D or 1D) before applying the hash function and then aggregate them into a single feature. Comparative evaluations against state-of-the-art methods demonstrate Fact-Hash's superior memory efficiency, preserving quality and rendering speed. Fact-Hash saves memory usage by over one-third while maintaining the PSNR values compared to previous encoding methods. The on-device experiment validates the superiority of Fact-Hash compared to alternative positional encoding methods in computational efficiency and energy consumption. These findings highlight Fact-Hash as a promising solution to improve feature grid representation, address memory constraints, and improve quality in various applications. Project page: https://facthash.github.io/

cs.CV↗

arXiv2026

PAVAS: Physics-Aware Video-to-Audio Synthesis

Recent advances in Video-to-Audio (V2A) generation have achieved impressive perceptual quality and temporal synchronization, yet most models remain appearance-driven, capturing visual-acoustic correlations without considering the physical factors that shape real-world sounds. We present Physics-Aware Video-to-Audio Synthesis (PAVAS), a method that incorporates physical reasoning into a latent diffusion-based V2A generation through the Physics-Driven Audio Adapter (Phy-Adapter). The adapter receives object-level physical parameters estimated by the Physical Parameter Estimator (PPE), which uses a Vision-Language Model (VLM) to infer the moving-object mass and a segmentation-based dynamic 3D reconstruction module to recover its motion trajectory for velocity computation. These physical cues enable the model to synthesize sounds that reflect underlying physical factors. To assess physical realism, we curate VGG-Impact, a benchmark focusing on object-object interactions, and introduce Audio-Physics Correlation Coefficient (APCC), an evaluation metric that measures consistency between physical and auditory attributes. Comprehensive experiments show that PAVAS produces physically plausible and perceptually coherent audio, outperforming existing V2A models in both quantitative and qualitative evaluations. Visit https://physics-aware-video-to-audio-synthesis.github.io for demo videos.

cs.CV↗

arXiv2026

Early Failure Detection and Intervention in Video Diffusion Models

Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to know during inference whether a generation will succeed or fail, incurring high computational cost due to trial-and-error regeneration. To address this, we propose an early failure detection and diagnostic intervention pipeline for latent T2V diffusion models. For detection, we design a Real-time Inspection (RI) module that converts latents into intermediate video previews, enabling the use of established text-video alignment scorers for inspection in the RGB space. The RI module completes the conversion and inspection process in just 39.2ms. This is highly efficient considering that CogVideoX-5B requires 4.3s per denoising step when generating a 480p, 49-frame video on an NVIDIA A100 GPU. Subsequently, we trigger a hierarchical and early-exit intervention pipeline only when failure is predicted. Experiments on CogVideoX-5B and Wan2.1-1.3B demonstrate consistency gains on VBench with up to 2.64 times less time overhead compared to post-hoc regeneration. Our method also generalizes to a higher-capacity setting, remaining effective on Wan2.1-14B with 720p resolution and 81-frame generation. Furthermore, our pipeline is plug-and-play and orthogonal to existing techniques, showing seamless compatibility with prompt refinement and sampling guidance methods. We also provide evidence that failure signals emerge early in the denoising process and are detectable within intermediate video previews using standard vision-language evaluators.

cs.CV↗

arXiv2026

HDR-NSFF: High Dynamic Range Neural Scene Flow Fields

Radiance of real-world scenes typically spans a much wider dynamic range than what standard cameras can capture. While conventional HDR methods merge alternating-exposure frames, these approaches are inherently constrained to 2D pixel-level alignment, often leading to ghosting artifacts and temporal inconsistency in dynamic scenes. To address these limitations, we present HDR-NSFF, a paradigm shift from 2D-based merging to 4D spatio-temporal modeling. Our framework reconstructs dynamic HDR radiance fields from alternating-exposure monocular videos by representing the scene as a continuous function of space and time, and is compatible with both neural radiance field and 4D Gaussian Splatting (4DGS) based dynamic representations. This unified end-to-end pipeline explicitly models HDR radiance, 3D scene flow, geometry, and tone-mapping, ensuring physical plausibility and global coherence. We further enhance robustness by (i) extending semantic-based optical flow with DINO features to achieve exposure-invariant motion estimation, and (ii) incorporating a generative prior as a regularizer to compensate for limited observation in monocular captures and saturation-induced information loss. To evaluate HDR space-time view synthesis, we present the first real-world HDR-GoPro dataset specifically designed for dynamic HDR scenes. Experiments demonstrate that HDR-NSFF recovers fine radiance details and coherent dynamics even under challenging exposure variations, thereby achieving state-of-the-art performance in novel space-time view synthesis. Project page: https://shin-dong-yeon.github.io/HDR-NSFF/

cs.CV↗

arXiv2026

LiDAR-Anchored Collaborative Distillation for Robust 2D Representations

As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks, including those related to vision-based systems. Nevertheless, pre-trained 2D image encoders fall short in conducting the task under noisy and adverse weather conditions beyond clear daytime scenes, which require for robust visual perception. To address these issues, we propose a novel self-supervised approach, \textbf{Collaborative Distillation}, which leverages 3D LiDAR as self-supervision to improve robustness to noisy and adverse weather conditions in 2D image encoders while retaining their original capabilities. Our method outperforms competing methods in various downstream tasks across diverse conditions and exhibits strong generalization ability. In addition, our method also improves 3D awareness stemming from LiDAR's characteristics. This advancement highlights our method's practicality and adaptability in real-world scenarios.

cs.CV↗

arXiv2026

ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptation

We introduce ELITE, an Efficient Gaussian head avatar synthesis from a monocular video via Learned Initialization and TEst-time generative adaptation. Prior works rely either on a 3D data prior or a 2D generative prior to compensate for missing visual cues in monocular videos. However, 3D data prior methods often struggle to generalize in-the-wild, while 2D generative prior methods are computationally heavy and prone to identity hallucination. We identify a complementary synergy between these two priors and design an efficient system that achieves high-fidelity animatable avatar synthesis with strong in-the-wild generalization. Specifically, we introduce a feed-forward Mesh2Gaussian Prior Model (MGPM) that enables fast initialization of a Gaussian avatar. To further bridge the domain gap at test time, we design a test-time generative adaptation stage, leveraging both real and synthetic images as supervision. Unlike previous full diffusion denoising strategies that are slow and hallucination-prone, we propose a rendering-guided single-step diffusion enhancer that restores missing visual details, grounded on Gaussian avatar renderings. Our experiments demonstrate that ELITE produces visually superior avatars to prior works, even for challenging expressions, while achieving 60x faster synthesis than the 2D generative prior method.

cs.CV↗

arXiv2025

FacEDiT: Unified Talking Face Editing and Generation via Facial Motion Infilling

Talking face editing and face generation have often been studied as distinct problems. In this work, we propose viewing both not as separate tasks but as subtasks of a unifying formulation, speech-conditional facial motion infilling. We explore facial motion infilling as a self-supervised pretext task that also serves as a unifying formulation of dynamic talking face synthesis. To instantiate this idea, we propose FacEDiT, a speech-conditional Diffusion Transformer trained with flow matching. Inspired by masked autoencoders, FacEDiT learns to synthesize masked facial motions conditioned on surrounding motions and speech. This formulation enables both localized generation and edits, such as substitution, insertion, and deletion, while ensuring seamless transitions with unedited regions. In addition, biased attention and temporal smoothness constraints enhance boundary continuity and lip synchronization. To address the lack of a standard editing benchmark, we introduce FacEDiTBench, the first dataset for talking face editing, featuring diverse edit types and lengths, along with new evaluation metrics. Extensive experiments validate that talking face editing and generation emerge as subtasks of speech-conditional motion infilling; FacEDiT produces accurate, speech-aligned facial edits with strong identity preservation and smooth visual continuity while generalizing effectively to talking face generation.

cs.CV↗

arXiv2025

Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching

Instance-level image retrieval aims to find images containing the same object as a given query, despite variations in size, position, or appearance. To address this challenging task, we propose Patchify, a simple yet effective patch-wise retrieval framework that offers high performance, scalability, and interpretability without requiring fine-tuning. Patchify divides each database image into a small number of structured patches and performs retrieval by comparing these local features with a global query descriptor, enabling accurate and spatially grounded matching. To assess not just retrieval accuracy but also spatial correctness, we introduce LocScore, a localization-aware metric that quantifies whether the retrieved region aligns with the target object. This makes LocScore a valuable diagnostic tool for understanding and improving retrieval behavior. We conduct extensive experiments across multiple benchmarks, backbones, and region selection strategies, showing that Patchify outperforms global methods and complements state-of-the-art reranking pipelines. Furthermore, we apply Product Quantization for efficient large-scale retrieval and highlight the importance of using informative features during compression, which significantly boosts performance. Project website: https://wons20k.github.io/PatchwiseRetrieval/

cs.CV↗

arXiv2025

RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models

Image retouching not only enhances visual quality but also serves as a means of expressing personal preferences and emotions. However, existing learning-based approaches require large-scale paired data and operate as black boxes, making the retouching process opaque and limiting their adaptability to handle diverse, user- or image-specific adjustments. In this work, we propose RetouchLLM, a training-free white-box image retouching system, which requires no training data and performs interpretable, code-based retouching directly on high-resolution images. Our framework progressively enhances the image in a manner similar to how humans perform multi-step retouching, allowing exploration of diverse adjustment paths. It comprises of two main modules: a visual critic that identifies differences between the input and reference images, and a code generator that produces executable codes. Experiments demonstrate that our approach generalizes well across diverse retouching styles, while natural language-based user interaction enables interpretable and controllable adjustments tailored to user intent.

cs.CV↗

arXiv2025

AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation

In this paper, we address the task of multimodal-to-speech generation, which aims to synthesize high-quality speech from multiple input modalities: text, video, and reference audio. This task has gained increasing attention due to its wide range of applications, such as film production, dubbing, and virtual avatars. Despite recent progress, existing methods still suffer from limitations in speech intelligibility, audio-video synchronization, speech naturalness, and voice similarity to the reference speaker. To address these challenges, we propose AlignDiT, a multimodal Aligned Diffusion Transformer that generates accurate, synchronized, and natural-sounding speech from aligned multimodal inputs. Built upon the in-context learning capability of the DiT architecture, AlignDiT explores three effective strategies to align multimodal representations. Furthermore, we introduce a novel multimodal classifier-free guidance mechanism that allows the model to adaptively balance information from each modality during speech synthesis. Extensive experiments demonstrate that AlignDiT significantly outperforms existing methods across multiple benchmarks in terms of quality, synchronization, and speaker similarity. Moreover, AlignDiT exhibits strong generalization capability across various multimodal tasks, such as video-to-speech synthesis and visual forced alignment, consistently achieving state-of-the-art performance. The demo page is available at https://mm.kaist.ac.kr/projects/AlignDiT.

cs.CV↗

arXiv2025

Automated Model Discovery via Multi-modal & Multi-step Pipeline

Automated model discovery is the process of automatically searching and identifying the most appropriate model for a given dataset over a large combinatorial search space. Existing approaches, however, often face challenges in balancing the capture of fine-grained details with ensuring generalizability beyond training data regimes with a reasonable model complexity. In this paper, we present a multi-modal \& multi-step pipeline for effective automated model discovery. Our approach leverages two vision-language-based modules (VLM), AnalyzerVLM and EvaluatorVLM, for effective model proposal and evaluation in an agentic way. AnalyzerVLM autonomously plans and executes multi-step analyses to propose effective candidate models. EvaluatorVLM assesses the candidate models both quantitatively and perceptually, regarding the fitness for local details and the generalibility for overall trends. Our results demonstrate that our pipeline effectively discovers models that capture fine details and ensure strong generalizability. Additionally, extensive ablation studies show that both multi-modality and multi-step reasoning play crucial roles in discovering favorable models.

cs.AI↗

arXiv2025

Learning Correlation-aware Aleatoric Uncertainty for 3D Hand Pose Estimation

3D hand pose estimation is a fundamental task in understanding human hands. However, accurately estimating 3D hand poses remains challenging due to the complex movement of hands, self-similarity, and frequent occlusions. In this work, we address two limitations: the inability of existing 3D hand pose estimation methods to estimate aleatoric (data) uncertainty, and the lack of uncertainty modeling that incorporates joint correlation knowledge, which has not been thoroughly investigated. To this end, we introduce aleatoric uncertainty modeling into the 3D hand pose estimation framework, aiming to achieve a better trade-off between modeling joint correlations and computational efficiency. We propose a novel parameterization that leverages a single linear layer to capture intrinsic correlations among hand joints. This is enabled by formulating the hand joint output space as a probabilistic distribution, allowing the linear layer to capture joint correlations. Our proposed parameterization is used as a task head layer, and can be applied as an add-on module on top of the existing models. Our experiments demonstrate that our parameterization for uncertainty modeling outperforms existing approaches. Furthermore, the 3D hand pose estimation model equipped with our uncertainty head achieves favorable accuracy in 3D hand pose estimation while introducing new uncertainty modeling capability to the model. The project page is available at https://hand-uncertainty.github.io/.

cs.CV↗

arXiv2025

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

Human motion is inherently continuous and dynamic, posing significant challenges for generative models. While discrete generation methods are widely used, they suffer from limited expressiveness and frame-wise noise artifacts. In contrast, continuous approaches produce smoother, more natural motion but often struggle to adhere to conditioning signals due to high-dimensional complexity and limited training data. To resolve this 'discord' between discrete and continuous representations we introduce DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding, a novel method that leverages rectified flow to decode discrete motion tokens in the continuous, raw motion space. Our core idea is to frame token decoding as a conditional generation task, ensuring that DisCoRD captures fine-grained dynamics and achieves smoother, more natural motions. Compatible with any discrete-based framework, our method enhances naturalness without compromising faithfulness to the conditioning signals on diverse settings. Extensive evaluations demonstrate that DisCoRD achieves state-of-the-art performance, with FID of 0.032 on HumanML3D and 0.169 on KIT-ML. These results establish DisCoRD as a robust solution for bridging the divide between discrete efficiency and continuous realism. Project website: https://whwjdqls.github.io/discord-motion/

cs.CV↗

arXiv2025

JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers

We present JointDiT, a diffusion transformer that models the joint distribution of RGB and depth. By leveraging the architectural benefit and outstanding image prior of the state-of-the-art diffusion transformer, JointDiT not only generates high-fidelity images but also produces geometrically plausible and accurate depth maps. This solid joint distribution modeling is achieved through two simple yet effective techniques that we propose, namely, adaptive scheduling weights, which depend on the noise levels of each modality, and the unbalanced timestep sampling strategy. With these techniques, we train our model across all noise levels for each modality, enabling JointDiT to naturally handle various combinatorial generation tasks, including joint generation, depth estimation, and depth-conditioned image generation by simply controlling the timesteps of each branch. JointDiT demonstrates outstanding joint generation performance. Furthermore, it achieves comparable results in depth estimation and depth-conditioned image generation, suggesting that joint distribution modeling can serve as a viable alternative to conditional generation. The project page is available at https://byungki-k.github.io/JointDiT/.

cs.CV↗

arXiv2025

Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild

Recent monocular 3D shape reconstruction methods have shown promising zero-shot results on object-segmented images without any occlusions. However, their effectiveness is significantly compromised in real-world conditions, due to imperfect object segmentation by off-the-shelf models and the prevalence of occlusions. To effectively address these issues, we propose a unified regression model that integrates segmentation and reconstruction, specifically designed for occlusion-aware 3D shape reconstruction. To facilitate its reconstruction in the wild, we also introduce a scalable data synthesis pipeline that simulates a wide range of variations in objects, occluders, and backgrounds. Training on our synthetic data enables the proposed model to achieve state-of-the-art zero-shot results on real-world images, using significantly fewer parameters than competing approaches.

cs.CV↗

arXiv2025

VSC: Visual Search Compositional Text-to-Image Diffusion Model

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts containing multiple attribute-object pairs. This challenge primarily arises from the limitations of commonly used text encoders, such as CLIP, which can fail to encode complex linguistic relationships and modifiers effectively. Existing approaches have attempted to mitigate these issues through attention map control during inference and the use of layout information or fine-tuning during training, yet they face performance drops with increased prompt complexity. In this work, we introduce a novel compositional generation method that leverages pairwise image embeddings to improve attribute-object binding. Our approach decomposes complex prompts into sub-prompts, generates corresponding images, and computes visual prototypes that fuse with text embeddings to enhance representation. By applying segmentation-based localization training, we address cross-attention misalignment, achieving improved accuracy in binding multiple attributes to objects. Our approaches outperform existing compositional text-to-image diffusion models on the benchmark T2I CompBench, achieving better image quality, evaluated by humans, and emerging robustness under scaling number of binding pairs in the prompt.

cs.CV↗

arXiv2025

VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models

We present VoiceCraft-Dub, a novel approach for automated video dubbing that synthesizes high-quality speech from text and facial cues. This task has broad applications in filmmaking, multimedia creation, and assisting voice-impaired individuals. Building on the success of Neural Codec Language Models (NCLMs) for speech synthesis, our method extends their capabilities by incorporating video features, ensuring that synthesized speech is time-synchronized and expressively aligned with facial movements while preserving natural prosody. To inject visual cues, we design adapters to align facial features with the NCLM token space and introduce audio-visual fusion layers to merge audio-visual information within the NCLM framework. Additionally, we curate CelebV-Dub, a new dataset of expressive, real-world videos specifically designed for automated video dubbing. Extensive experiments show that our model achieves high-quality, intelligible, and natural speech synthesis with accurate lip synchronization, outperforming existing methods in human perception and performing favorably in objective evaluations. We also adapt VoiceCraft-Dub for the video-to-speech task, demonstrating its versatility for various applications.

cs.CV↗