arXiv subjects

De Wen Soh

Publications and source records attributed to De Wen Soh.

17 recordsLinked to original sources

arXiv2026

Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion

Guided depth completion methods heavily depend on RGB quality and alignment, while unguided ones often suffer from limited precision due to the absence of explicit visual cues. In this paper, we present Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion (GUDC), a new completion paradigm that innovatively bridges advanced 2D generative models with unguided depth completion, enabling semantics-aware depth inference without real RGB inputs. Our key idea is to exploit ControlNet's powerful depth-conditioned generation capability to synthesize pseudo-images directly from sparse depth, effectively converting the original unguided setting into a semantics-guided one. To address the potential image-depth misalignment caused by depth sparsity, we propose a multi-level dense-to-sparse representation distillation strategy for ControlNet fine-tuning, where dense-depth features act as teacher signals to distill consistent structural representations for sparse-depth inputs. Furthermore, during pseudo-image-guided completion, we propose a pseudo-image semantic attention fusion module to adaptively extract informative semantic cues from pseudo-images while suppressing artifacts (e.g., texture hallucinations). Extensive experiments on KITTI and NYUv2 validate that our GUDC achieves superior accuracy and robustness over existing methods.

cs.CV↗

arXiv2026

Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes

Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful intent coexist. These complexities highlight the need for explainable meme understanding systems that can provide reliable and structured reasoning to support both accurate classification and human interpretability. However, existing multimodal classifiers either overlook these interdependencies or provide only limited interpretability. In this paper, we introduce MAR-12, a novel framework that leverages Vision Language Models (VLMs) for meme detection and understanding in settings where humorous and hateful elements may coexist. The framework first interprets each meme through twelve structured perspectives derived from humor and hate theories. It then applies a role-aware soft-gated attention mechanism to learn how much each perspective should contribute, followed by a prototype-based classifier for the final prediction. Finally, explanations are synthesized using both perspective-specific reasoning and learned attention weights, ensuring transparent and context-grounded justifications. We evaluate MAR-12 on the PrideMM and Memotion datasets, where it achieves up to 80.3% accuracy for humor detection and 75.9% accuracy for hate detection, outperforming state-of-the-art approaches. Furthermore, both human and GPT-4-based evaluations confirm that MAR-12 produces coherent and persuasive explanations, particularly for memes in which humorous and harmful cues co-occur.

cs.AI↗

arXiv2026

I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisition

Multimodal memes are dynamic and often require up to date background knowledge for interpretation. Existing methods often overlook such knowledge or rely on fixed parametric knowledge of pretrained models that may be incomplete, outdated, or unavailable for emerging memes. We introduce Query Retrieve Conclude, a zero shot framework that identifies missing knowledge, retrieves open web evidence, and synthesizes evidence grounded background knowledge for meme understanding and detection. We also introduce a curated meme understanding benchmark of recent memes from 2024 to 2026 with external background knowledge annotations. Experiments on three meme understanding datasets and five meme detection tasks show that our framework improves knowledge recovery, meme understanding and downstream detection over zero shot baselines.

cs.AI↗

arXiv2026

Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking

Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often struggle in scenarios that demand fine-grained understanding of semantic and visual structural information within video frames. Text-to-image diffusion models are well known for their ability to generate images that accurately reflect the semantics and structures described in the input prompt, demonstrating a strong grasp of visual semantics and structures. Building on this capability, we approach the unsupervised tracking from a new perspective by exploiting the rich semantic knowledge encoded in pretrained text-to-image diffusion models. To adapt the diffusion models, which are originally developed for image generation, to the tracking task, we reinterpret the models as a bridge between text and image modalities. This connection is realized through the cross-attention mechanism: when both text and an image are input into the models, they highlight the regions of the image that are semantically aligned with the text in the cross-attention maps. We therefore learn a prompt that represents the tracking target and activates its corresponding region in the cross-attention map for each frame, which enables object tracking with the diffusion model. Specifically, our method Diff-Tracking is composed of two main components: an initial prompt learner and an online prompt updater. The initial prompt learner generates a prompt that captures the target object in the first frame, allowing the diffusion model to identify the target. The online prompt updater refines the prompt based on motion information, enabling consistent tracking across video frames. We evaluate our approach on six challenging tracking datasets demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2026

VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation

This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panoramic reprojection over multi-view reconstructed 3D models by leveraging the intrinsic 3D consistency of VGGT-like foundation models, thereby unifying fragmented per-view reasoning into a coherent panoramic understanding. To achieve robust and accurate estimation, VGGT-360 integrates three plug-and-play modules that form a unified panorama-to-3D-to-depth framework: (i) Uncertainty-guided adaptive projection slices panoramas into perspective views to bridge the domain gap between panoramic inputs and VGGT's perspective prior. It estimates gradient-based uncertainty to allocate denser views to geometry-poor regions, yielding geometry-informative inputs for VGGT. (ii) Structure-saliency enhanced attention strengthens VGGT's robustness during 3D reconstruction by injecting structure-aware confidence into its attention layers, guiding focus toward geometrically reliable regions and enhancing cross-view coherence. (iii) Correlation-weighted 3D model correction refines the reconstructed 3D model by reweighting overlapping points using attention-inferred correlation scores, providing a consistent geometric basis for accurate panoramic reprojection. Extensive experiments show that VGGT-360 outperforms both trained and training-free state-of-the-art methods across multiple resolutions and diverse indoor and outdoor datasets.

cs.CV↗

arXiv2026

Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detection

Humorous memes blend visual and textual cues to convey irony, satire, or social commentary, posing unique challenges for AI systems that must interpret intent rather than surface correlations. Existing multimodal or prompting-based models generate explanations for humor but operate in an open loop,lacking the ability to critique or refine their reasoning once a prediction is made. We propose FLoReNce, an agentic feedback reasoning framework that treats meme understanding as a closed-loop process during learning and an open-loop process during inference. In the closed loop, a reasoning agent is critiqued by a judge; the error and semantic feedback are converted into control signals and stored in a feedback-informed, non-parametric knowledge base. At inference, the model retrieves similar judged experiences from this KB and uses them to modulate its prompt, enabling better, self-aligned reasoning without finetuning. On the PrideMM dataset, FLoReNce improves both predictive performance and explanation quality over static multimodal baselines, showing that feedback-regulated prompting is a viable path to adaptive meme humor understanding.

cs.AI↗

arXiv2025

OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects

Free-moving object reconstruction from monocular video remains challenging, particularly without reliable pose or depth cues and under arbitrary object motion. We introduce OnlineSplatter, a novel online feed-forward framework generating high-quality, object-centric 3D Gaussians directly from RGB frames without requiring camera pose, depth priors, or bundle optimization. Our approach anchors reconstruction using the first frame and progressively refines the object representation through a dense Gaussian primitive field, maintaining constant computational cost regardless of video sequence length. Our core contribution is a dual-key memory module combining latent appearance-geometry keys with explicit directional keys, robustly fusing current frame features with temporally aggregated object states. This design enables effective handling of free-moving objects via spatial-guided memory readout and an efficient sparsification mechanism, ensuring comprehensive yet compact object coverage. Evaluations on real-world datasets demonstrate that OnlineSplatter significantly outperforms state-of-the-art pose-free reconstruction baselines, consistently improving with more observations while maintaining constant memory and runtime.

cs.CV↗

arXiv2025

Visual Prompting for One-shot Controllable Video Editing without Inversion

One-shot controllable video editing (OCVE) is an important yet challenging task, aiming to propagate user edits that are made -- using any image editing tool -- on the first frame of a video to all subsequent frames, while ensuring content consistency between edited frames and source frames. To achieve this, prior methods employ DDIM inversion to transform source frames into latent noise, which is then fed into a pre-trained diffusion model, conditioned on the user-edited first frame, to generate the edited video. However, the DDIM inversion process accumulates errors, which hinder the latent noise from accurately reconstructing the source frames, ultimately compromising content consistency in the generated edited frames. To overcome it, our method eliminates the need for DDIM inversion by performing OCVE through a novel perspective based on visual prompting. Furthermore, inspired by consistency models that can perform multi-step consistency sampling to generate a sequence of content-consistent images, we propose a content consistency sampling (CCS) to ensure content consistency between the generated edited frames and the source frames. Moreover, we introduce a temporal-content consistency sampling (TCS) based on Stein Variational Gradient Descent to ensure temporal consistency across the edited frames. Extensive experiments validate the effectiveness of our approach.

cs.CV↗

arXiv2025

POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation

Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses. This paper introduces POPEN, a novel framework designed to address these issues and achieve improved results. POPEN includes a preference-based optimization method to finetune the LVLM, aligning it more closely with human preferences and thereby generating better text responses and segmentation results. Additionally, POPEN introduces a preference-based ensemble method for inference, which integrates multiple outputs from the LVLM using a preference-score-based attention mechanism for refinement. To better adapt to the segmentation task, we incorporate several task-specific designs in our POPEN framework, including a new approach for collecting segmentation preference data with a curriculum learning mechanism, and a novel preference optimization loss to refine the segmentation capability of the LVLM. Experiments demonstrate that our method achieves state-of-the-art performance in reasoning segmentation, exhibiting minimal hallucination in text responses and the highest segmentation accuracy compared to previous advanced methods like LISA and PixelLM. Project page is https://lanyunzhu.site/POPEN/

cs.CV↗

arXiv2025

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

Human motion generation and editing are key components of computer vision. However, current approaches in this field tend to offer isolated solutions tailored to specific tasks, which can be inefficient and impractical for real-world applications. While some efforts have aimed to unify motion-related tasks, these methods simply use different modalities as conditions to guide motion generation. Consequently, they lack editing capabilities, fine-grained control, and fail to facilitate knowledge sharing across tasks. To address these limitations and provide a versatile, unified framework capable of handling both human motion generation and editing, we introduce a novel paradigm: \textbf{Motion-Condition-Motion}, which enables the unified formulation of diverse tasks with three concepts: source motion, condition, and target motion. Based on this paradigm, we propose a unified framework, \textbf{MotionLab}, which incorporates rectified flows to learn the mapping from source motion to target motion, guided by the specified conditions. In MotionLab, we introduce the 1) MotionFlow Transformer to enhance conditional generation and editing without task-specific modules; 2) Aligned Rotational Position Encoding to guarantee the time synchronization between source motion and target motion; 3) Task Specified Instruction Modulation; and 4) Motion Curriculum Learning for effective multi-task learning and knowledge sharing across tasks. Notably, our MotionLab demonstrates promising generalization capabilities and inference efficiency across multiple benchmarks for human motion. Our code and additional video results are available at: https://diouo.github.io/motionlab.github.io/.

cs.CV↗

arXiv2024

GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians

Recently, with the development of Neural Radiance Fields and Gaussian Splatting, 3D reconstruction techniques have achieved remarkably high fidelity. However, the latent representations learnt by these methods are highly entangled and lack interpretability. In this paper, we propose a novel part-aware compositional reconstruction method, called GaussianBlock, that enables semantically coherent and disentangled representations, allowing for precise and physical editing akin to building blocks, while simultaneously maintaining high fidelity. Our GaussianBlock introduces a hybrid representation that leverages the advantages of both primitives, known for their flexible actionability and editability, and 3D Gaussians, which excel in reconstruction quality. Specifically, we achieve semantically coherent primitives through a novel attention-guided centering loss derived from 2D semantic priors, complemented by a dynamic splitting and fusion strategy. Furthermore, we utilize 3D Gaussians that hybridize with primitives to refine structural details and enhance fidelity. Additionally, a binding inheritance strategy is employed to strengthen and maintain the connection between the two. Our reconstructed scenes are evidenced to be disentangled, compositional, and compact across diverse benchmarks, enabling seamless, direct and precise editing while maintaining high quality.

cs.CV↗

arXiv2023

On the Identifiability from Modulo Measurements under DFT Sensing Matrix

Modulo sampling (MS) has been recently introduced to enhance the dynamic range of conventional ADCs by applying a modulo operator before sampling. This paper examines the identifiability of a measurement model where measurements are taken using a discrete Fourier transform (DFT) sensing matrix, followed by a modulo operator (modulo-DFT). Firstly, we derive a necessary and sufficient condition for the unique identification of the modulo-DFT sensing model based on the number of measurements and the indices of zero elements in the original signal. Then, we conduct a deeper analysis of three specific cases: when the number of measurements is a power of $2$, a prime number, and twice a prime number. Additionally, we investigate the identifiability of periodic bandlimited (PBL) signals under MS, which can be considered as the modulo-DFT sensing model with additional symmetric and conjugate constraints on the original signal. We also provide a necessary and sufficient condition based solely on the number of samples in one period for the unique identification of the PBL signal under MS, though with an ambiguity in the direct current (DC) component. Furthermore, we show that when the oversampling factor exceeds $3(1+1/P)$, the PBL signal can be uniquely identified with an ambiguity in the DC component, where $P$ is the number of harmonics, including the fundamental component, in the positive frequency part. Finally, we also present a recovery algorithm that estimates the original signal by solving integer linear equations, and we conduct simulations to validate our conclusions.

cs.IT↗

arXiv2023

One-Bit-Aided Modulo Sampling for DOA Estimation

Modulo sampling has recently drawn a great deal of attention for cutting-edge applications, due to overcoming the barrier of information loss through sensor saturation and clipping. This is a significant problem, especially when the range of signal amplitudes is unknown or in the near-far case. To overcome this fundamental bottleneck, we propose a one-bit-aided (1bit-aided) modulo sampling scheme for direction-of-arrival (DOA) estimation. On the one hand, one-bit quantization involving a simple comparator offers the advantages of low-cost and low-complexity implementation. On the other hand, one-bit quantization provides an estimate of the normalized covariance matrix of the unquantized measurements via the arcsin law. The estimate of the normalized covariance matrix is used to implement blind integer-forcing (BIF) decoder to unwrap the modulo samples to construct the covariance matrix, and subspace methods can be used to perform the DOA estimation. Our approach named as 1bit-aided-BIF addresses the near-far problem well and overcomes the intrinsic low dynamic range of one-bit quantization. Numerical experiments validate the excellent performance of the proposed algorithm.

eess.SP↗

arXiv2023

Enhancing Few-shot NER with Prompt Ordering based Data Augmentation

Recently, data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER). However, conventional NER DA methods are mostly aimed at sequence labeling models, i.e., token-level classification, and few are compatible with unified autoregressive generation frameworks, which can handle a wider range of NER tasks, such as nested NER. Furthermore, these generation frameworks have a strong assumption that the entities will appear in the target sequence with the same left-to-right order as the source sequence. In this paper, we claim that there is no need to keep this strict order, and more diversified but reasonable target entity sequences can be provided during the training stage as a novel DA method. Nevertheless, a naive mixture of augmented data can confuse the model since one source sequence will then be paired with different target sequences. Therefore, we propose a simple but effective Prompt Ordering based Data Augmentation (PODA) method to improve the training of unified autoregressive generation frameworks under few-shot NER scenarios. Experimental results on three public NER datasets and further analyses demonstrate the effectiveness of our approach.

cs.CL↗

arXiv2022

Line Spectral Estimation via Unlimited Sampling

Frequency Modulated Continuous Wave (FMCW) radar has been widely applied in automotive anti-collision systems, automatic cruise control, and indoor monitoring. However, conventional analog-to-digital converters (ADCs) can suffer from significant information loss when strong and weak targets coexist in ranging applications. To address this issue, the Unlimited Sampling (US) strategy was proposed, which applies a modulo operator prior to sampling. In this paper, we investigate the range estimation problem using FMCW radar in the context of US, which can be formulated as a one-dimensional line spectral estimation (LSE) via US. By exploiting the oversampling property and proving that the leakage onto a certain frequency band can be controlled, we establish an integer optimization problem in the Fourier and first-order difference domain. We then propose a dynamic programming (DP) based algorithm followed by the orthogonal matching pursuit (OMP) method to solve it. In addition, a two-stage US LSE (USLSE) is proposed, where the line spectral signal is first recovered by iteratively executing DP and OMP, and then the parameters are estimated by applying a state-of-the-art LSE algorithm. Substantial numerical simulations and real experiments demonstrate that the proposed algorithm, USLSE, outperforms existing algorithms.

eess.SP↗

arXiv2021

Joint Network Topology Inference via Structured Fusion Regularization

Joint network topology inference represents a canonical problem of jointly learning multiple graph Laplacian matrices from heterogeneous graph signals. In such a problem, a widely employed assumption is that of a simple common component shared among multiple networks. However, in practice, a more intricate topological pattern, comprising simultaneously of sparse, homogeneity and heterogeneity components, would exhibit in multiple networks. In this paper, we propose a general graph estimator based on a novel structured fusion regularization that enables us to jointly learn multiple graph Laplacian matrices with such complex topological patterns, and enjoys both high computational efficiency and rigorous theoretical guarantee. Moreover, in the proposed regularization term, the topological pattern among networks is characterized by a Gram matrix, endowing our graph estimator with the ability of flexible modelling different types of topological patterns by different choices of the Gram matrix. Computationally, the regularization term, coupling the parameters together, makes the formulated optimization problem intractable and thus, we develop a computationally-scalable algorithm based on the alternating direction method of multipliers (ADMM) to solve it efficiently. Theoretically, we provide a theoretical analysis of the proposed graph estimator, which establishes a non-asymptotic bound of the estimation error under the high-dimensional setting and reflects the effect of several key factors on the convergence rate of our algorithm. Finally, the superior performance of the proposed method is illustrated through simulated and real data examples.

math.ST↗

arXiv2018

Identifiability in Gaussian Graphical Models

In high-dimensional graph learning problems, some topological properties of the graph, such as bounded node degree or tree structure, are typically assumed to hold so that the sample complexity of recovering the graph structure can be reduced. With bounded degree or separability assumptions, quantified by a measure $k$, a $p$-dimensional Gaussian graphical model (GGM) can be learnt with sample complexity $\Omega (k \: \text{log} \: p)$. Our work in this paper aims to do away with these assumptions by introducing an algorithm that can identify whether a GGM indeed has these topological properties without any initial topological assumptions. We show that we can check whether a GGM has node degree bounded by $k$ with sample complexity $\Omega (k \: \text{log} \: p)$. More generally, we introduce the notion of a strongly K-separable GGM, and show that our algorithm can decide whether a GGM is strongly $k$-separable or not, with sample complexity $\Omega (k \: \text{log} \: p)$. We introduce the notion of a generalized feedback vertex set (FVS), an extension of the typical FVS, and show that we can use this identification technique to learn GGMs with generalized FVSs.

math.ST↗