arXiv subjects

Xinhao Cai

Publications and source records attributed to Xinhao Cai.

10 recordsLinked to original sources

arXiv2026

Music-to-Dance Generation via Atomic Movements

Music-driven dance generation aims to produce human motion that is both rhythmically synchronized and semantically consistent with music. While recent neural approaches have achieved impressive visual realism, they typically model motion as a continuous signal and neglect its compositional nature, making generated dances structurally incoherent and difficult to control. In this work, we introduce a structure-aware framework that models choreography as a sequence of atomic movements-semantically interpretable motion events that serve as the building blocks of dance. To construct this atomic movement vocabulary, we first segment large-scale dance data and cluster them into atomic movement groups. We then employ a large language model to semantically relabel and refine the clusters, yielding a set of interpretable and reusable atomic movements. Based on these atomic movement annotations, we design a two-stage generation framework that mirrors the human choreography process. In the atomic movement planning stage, the model predicts the type, duration, and timing of atomic movements conditioned on the input music, forming a symbolic dance allocation. In the completion stage, a transition-aware generator synthesizes smooth and stylistically coherent motion conditioned on the planned structure. Extensive experiments demonstrate that our method produces dances with significantly improved structural coherence, rhythmic alignment, and perceptual naturalness compared to existing baselines, while providing enhanced interpretability and controllable editing through explicit structural representation.

cs.CV↗

arXiv2026

PEARL: Geometry Aligns Semantics for Training-Free Open-Vocabulary Semantic Segmentation

Training-free open-vocabulary semantic segmentation (OVSS) promises rapid adaptation to new label sets without retraining. Yet, many methods rely on heavy post-processing or handle text and vision in isolation, leaving cross-modal geometry underutilized. Others introduce auxiliary vision backbones or multi-model pipelines, which increase complexity and latency while compromising design simplicity. We present PEARL, \textbf{\underline{P}}rocrust\textbf{\underline{e}}s \textbf{\underline{a}}lignment with text-awa\textbf{\underline{r}}e \textbf{\underline{L}}aplacian propagation, a compact two-step inference that follows an align-then-propagate principle. The Procrustes alignment step performs an orthogonal projection inside the last self-attention block, rotating keys toward the query subspace via a stable polar iteration. The text-aware Laplacian propagation then refines per-pixel logits on a small grid through a confidence-weighted, text-guided graph solve: text provides both a data-trust signal and neighbor gating, while image gradients preserve boundaries. In this work, our method is fully training-free, plug-and-play, and uses only fixed constants, adding minimal latency with a small per-head projection and a few conjugate-gradient steps. Our approach, PEARL, sets a new state-of-the-art in training-free OVSS without extra data or auxiliary backbones across standard benchmarks, achieving superior performance under both with-background and without-background protocols.

cs.CV↗

arXiv2026

Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation

In this paper, we propose \textbf{Iris}, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional feed-forward methods rely on massive training data, yet still miss details. Previous diffusion-based methods leverage rich generative priors yet struggle with synthetic-to-real domain transfer. Iris, in contrast, preserves fine details, generalizes strongly from synthetic to real scenes, and remains efficient with limited training data. To this end, we introduce a two-stage Priors-to-Geometry Deterministic (PGD) schedule: the prior stage uses Spectral-Gated Distillation (SGD) to transfer low-frequency real priors while leaving high-frequency details unconstrained, and the geometry stage applies Spectral-Gated Consistency (SGC) to enforce high-frequency fidelity while refining with synthetic ground truth. The two stages share weights and are executed with a high-to-low timestep schedule. Extensive experimental results confirm that Iris achieves significant improvements in MDE performance with strong in-the-wild generalization.

cs.CV↗

arXiv2026

PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection

Object detection in remote sensing images (RSIs) is challenged by the coexistence of geometric and spatial complexity: targets may appear with diverse aspect ratios, while spanning a wide range of object sizes under varied contexts. Existing RSI backbones address the two challenges separately, either by adopting anisotropic strip kernels to model slender targets or by using isotropic large kernels to capture broader context. However, such isolated treatments lead to complementary drawbacks: the strip-only design can disrupt spatial coherence for regular-shaped objects and weaken tiny details, whereas isotropic large kernels often introduce severe background noise and geometric mismatch for slender structures. In this paper, we extend PKINet, and present a powerful and efficient backbone that jointly handles both challenges within a unified paradigm named Poly Kernel Inception Network v2 (PKINet-v2). PKINet-v2 synergizes anisotropic axial-strip convolutions with isotropic square kernels and builds a multi-scope receptive field, preserving fine-grained local textures while progressively aggregating long-range context across scales. To enable efficient deployment, we further introduce a Heterogeneous Kernel Re-parameterization (HKR) Strategy that fuses all heterogeneous branches into a single depth-wise convolution for inference, eliminating fragmented kernel launches without accuracy loss. Extensive experiments on four widely-used benchmarks, including DOTA-v1.0, DOTA-v1.5, HRSC2016, and DIOR-R, demonstrate that PKINet-v2 achieves state-of-the-art accuracy while delivering a $\textbf{3.9}\times$ FPS acceleration compared to PKINet-v1, surpassing previous remote sensing backbones in both effectiveness and efficiency.

cs.CV↗

arXiv2025

Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis

This paper presents a generation-based debiasing framework for object detection. Prior debiasing methods are often limited by the representation diversity of samples, while naive generative augmentation often preserves the biases it aims to solve. Moreover, our analysis reveals that simply generating more data for rare classes is suboptimal due to two core issues: i) instance frequency is an incomplete proxy for the true data needs of a model, and ii) current layout-to-image synthesis lacks the fidelity and control to generate high-quality, complex scenes. To overcome this, we introduce the representation score (RS) to diagnose representational gaps beyond mere frequency, guiding the creation of new, unbiased layouts. To ensure high-quality synthesis, we replace ambiguous text prompts with a precise visual blueprint and employ a generative alignment strategy, which fosters communication between the detector and generator. Our method significantly narrows the performance gap for underrepresented object groups, \eg, improving large/rare instances by 4.4/3.6 mAP over the baseline, and surpassing prior L2I synthesis models by 15.9 mAP for layout accuracy in generated images.

cs.CV↗

arXiv2025

InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects

We propose a novel task of text-controlled human object interaction generation in 3D scenes with movable objects. Existing human-scene interaction datasets suffer from insufficient interaction categories and typically only consider interactions with static objects (do not change object positions), and the collection of such datasets with movable objects is difficult and costly. To address this problem, we construct the InteractMove dataset for Movable Human-Object Interaction in 3D Scenes by aligning existing human object interaction data with scene contexts, featuring three key characteristics: 1) scenes containing multiple movable objects with text-controlled interaction specifications (including same-category distractors requiring spatial and 3D scene context understanding), 2) diverse object types and sizes with varied interaction patterns (one-hand, two-hand, etc.), and 3) physically plausible object manipulation trajectories. With the introduction of various movable objects, this task becomes more challenging, as the model needs to identify objects to be interacted with accurately, learn to interact with objects of different sizes and categories, and avoid collisions between movable objects and the scene. To tackle such challenges, we propose a novel pipeline solution. We first use 3D visual grounding models to identify the interaction object. Then, we propose a hand-object joint affordance learning to predict contact regions for different hand joints and object parts, enabling accurate grasping and manipulation of diverse objects. Finally, we optimize interactions with local-scene modeling and collision avoidance constraints, ensuring physically plausible motions and avoiding collisions between objects and the scene. Comprehensive experiments demonstrate our method's superiority in generating physically plausible, text-compliant interactions compared to existing approaches.

cs.CV↗

arXiv2025

Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection

The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot classification and retrieval capabilities on various domains. However, CLIP's training remains computationally intensive, with high demands on both data processing and memory. To address these challenges, recent masking strategies have emerged, focusing on the selective removal of image patches to improve training efficiency. Although effective, these methods often compromise key semantic information, resulting in suboptimal alignment between visual features and text descriptions. In this work, we present a concise yet effective approach called Patch Generation-to-Selection to enhance CLIP's training efficiency while preserving critical semantic content. Our method introduces a gradual masking process in which a small set of candidate patches is first pre-selected as potential mask regions. Then, we apply Sobel edge detection across the entire image to generate an edge mask that prioritizes the retention of the primary object areas. Finally, similarity scores between the candidate mask patches and their neighboring patches are computed, with optimal transport normalization refining the selection process to ensure a balanced similarity matrix. Our approach, CLIP-PGS, sets new state-of-the-art results in zero-shot classification and retrieval tasks, achieving superior performance in robustness evaluation and language compositionality benchmarks.

cs.CV↗

arXiv2024

Training-free Video Temporal Grounding using Large-scale Pre-trained Models

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data collection costs, but they exhibit poor generalization capability under the across-dataset and out-of-distribution (OOD) settings. In this paper, we propose a Training-Free Video Temporal Grounding (TFVTG) approach that leverages the ability of pre-trained large models. A naive baseline is to enumerate proposals in the video and use the pre-trained visual language models (VLMs) to select the best proposal according to the vision-language alignment. However, most existing VLMs are trained on image-text pairs or trimmed video clip-text pairs, making it struggle to (1) grasp the relationship and distinguish the temporal boundaries of multiple events within the same video; (2) comprehend and be sensitive to the dynamic transition of events (the transition from one event to another) in the video. To address these issues, we propose leveraging large language models (LLMs) to analyze multiple sub-events contained in the query text and analyze the temporal order and relationships between these events. Secondly, we split a sub-event into dynamic transition and static status parts and propose the dynamic and static scoring functions using VLMs to better evaluate the relevance between the event and the description. Finally, for each sub-event description, we use VLMs to locate the top-k proposals and leverage the order and relationships between sub-events provided by LLMs to filter and integrate these proposals. Our method achieves the best performance on zero-shot video temporal grounding on Charades-STA and ActivityNet Captions datasets without any training and demonstrates better generalization capabilities in cross-dataset and OOD settings.

cs.CV↗

arXiv2024

Universal Organizer of SAM for Unsupervised Semantic Segmentation

Unsupervised semantic segmentation (USS) aims to achieve high-quality segmentation without manual pixel-level annotations. Existing USS models provide coarse category classification for regions, but the results often have blurry and imprecise edges. Recently, a robust framework called the segment anything model (SAM) has been proven to deliver precise boundary object masks. Therefore, this paper proposes a universal organizer based on SAM, termed as UO-SAM, to enhance the mask quality of USS models. Specifically, using only the original image and the masks generated by the USS model, we extract visual features to obtain positional prompts for target objects. Then, we activate a local region optimizer that performs segmentation using SAM on a per-object basis. Finally, we employ a global region optimizer to incorporate global image information and refine the masks to obtain the final fine-grained masks. Compared to existing methods, our UO-SAM achieves state-of-the-art performance.

cs.MM↗

arXiv2024

Poly Kernel Inception Network for Remote Sensing Detection

Object detection in remote sensing images (RSIs) often suffers from several increasing challenges, including the large variation in object scales and the diverse-ranging context. Prior methods tried to address these challenges by expanding the spatial receptive field of the backbone, either through large-kernel convolution or dilated convolution. However, the former typically introduces considerable background noise, while the latter risks generating overly sparse feature representations. In this paper, we introduce the Poly Kernel Inception Network (PKINet) to handle the above challenges. PKINet employs multi-scale convolution kernels without dilation to extract object features of varying scales and capture local context. In addition, a Context Anchor Attention (CAA) module is introduced in parallel to capture long-range contextual information. These two components work jointly to advance the performance of PKINet on four challenging remote sensing detection benchmarks, namely DOTA-v1.0, DOTA-v1.5, HRSC2016, and DIOR-R.

cs.CV↗