arXiv subjects

Weize Quan

Publications and source records attributed to Weize Quan.

At least 19 recordsLinked to original sources

arXiv2026

Object-Uni: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation

Unified models for visual understanding and generation have made rapid progress, yet they still lack the ability to understand and manipulate the spatial states of object instances. Existing models can describe objects in natural language, but they struggle to precisely represent continuous object poses and generate geometrically consistent images under target viewpoints. To mitigate this, we propose \emph{Object-Uni}, a unified model for object-centric spatial understanding and controllable generation. Specifically, we formulate object-centric spatial intelligence as a unified problem connecting pose perception, spatial reasoning, pose-conditioned generation, and object-centric novel view synthesis. We treat object pose as an explicit geometric variable shared by understanding and generation, rather than merely a prediction label or control signal. To make pose usable by multimodal large language models, we propose a viewpoint-based orientation abstraction that maps orientation into structured viewpoint descriptions while preserving continuous geometric supervision. We further construct an object-centric spatial benchmark (UniSpatial-80K) and train a unified model with an object-token-grounded pose anchor to associate each instance with its pose state. Experiments show that our model improves object-level pose understanding and pose-controllable generation, moving unified models from describing objects toward manipulating spatial states.

cs.CV↗

arXiv2026

MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement

View-based point cloud completion aims to recover a complete 3D shape from a partial point cloud, guided by a single-view image. However, existing approaches often suffer from limited performance due to weak modality alignment and limited self-geometry enhancement. To overcome these challenges, we propose a unified geometry-aware framework that integrates efficient modality alignment and adaptive geometry enhancement, mainly to address cross-modal geometric inconsistency of view-guided point cloud completion. Specifically, we propose a geometry-aware modality alignment by integrating a shared self-attention Transformer and cross-modality reconstruction supervision, which aims to bring features of the image and point cloud close to each other in a shared latent space describing the 3D object. To enhance the perception of global shape and local geometric details, we propose an adaptive geometry-aware self-attention module, which simultaneously considers local geometry-aware attention computation and the spatially-variant feature fusion. In addition, we apply a geometry-perceptive anchor refinement module to reorganize the anchor points (representing a local region of the shape) under appropriate supervision, further boosting the completion performance of our method. Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves superior performance over existing approaches. Our code will be available at https://github.com/weizequan/MAGE.

cs.CV↗

arXiv2026

COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models

Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grained composition recognition and struggle to turn such intent into controllable generation. We present COMPASS, the first unified multimodal framework that grounds composition-intent control in a single system spanning both composition perception and composition-guided generation, with a shared expert token $\tau_c$ as the central intent anchor. On the perception side, COMPASS injects composition expertise into an MoE backbone in a minimally invasive manner and distills the inferred intent into $\tau_c$. On the generation side, COMPASS reuses $\tau_c$ as a global conditioning signal that steers the denoising trajectory, effectively converting passive composition analysis into explicit layout control. To support systematic instruction-following composition learning and evaluation at scale, we construct Comp-11, a large-scale dataset with an 11-class taxonomy and reasoning-augmented annotations. Extensive experiments show that COMPASS substantially improves category-level composition understanding and delivers more composition-consistent, prompt-faithful generation than strong baselines.

cs.AI↗

arXiv2026

CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling

Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic consistency. Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors. Inspired by human design cognition, we present CasLayout, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages with explicit physical and semantic roles: (1) predicting furniture quantity and categories, (2) refining object sizes and feature embeddings, (3) modeling spatial relationships in a latent space, and (4) generating Oriented Bounding Boxes (OBBs). This decoupled architecture reduces data requirements and enables flexible integration of Large Language Models (LLMs) and Vision Language Models (VLMs) for zero-shot tasks such as image-to-scene generation. To maintain physical validity within complex floor plans, we explicitly model building elements (e.g., walls, doors, and windows) as conditional constraints. Furthermore, to address the high entropy of dense relation graphs, we introduce a sparse relation graph formulation aligned with human spatial descriptions. By encoding these sparse graphs into a compact latent space using a bidirectional Variational Autoencoder (VAE), the proposed framework provides enhanced relational controllability, allowing generated layouts to better respect functional organization. Experiments demonstrate that CasLayout achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.

cs.CV↗

arXiv2026

RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution

Recent advances in generative super-resolution (SR) have greatly improved visual realism, yet existing evaluation and optimization frameworks remain misaligned with human perception. Full-Reference and No-Reference metrics often fail to reflect perceptual preference, either penalizing semantically plausible details due to pixel misalignment or favoring visually sharp but inconsistent artifacts. Moreover, most SR methods rely on ground-truth (GT)-dependent distribution matching, which does not necessarily correspond to human judgments. In this work, we propose RefReward-SR, a low-resolution (LR) reference-aware reward model for preference-aligned SR. Instead of relying on GT supervision or NR evaluation, RefReward-SR assesses high-resolution (HR) reconstructions conditioned on their LR inputs, treating the LR image as a semantic anchor. Leveraging the visual-linguistic priors of a Multimodal Large Language Models (MLLM), it evaluates semantic consistency and plausibility in a reasoning-aware manner. To support this paradigm, we construct RefSR-18K, the first large-scale LR-conditioned preference dataset for SR, providing pairwise rankings based on LR-HR consistency and HR naturalness. We fine-tune the MLLM with Group Relative Policy Optimization (GRPO) using LR-conditioned ranking rewards, and further integrate GRPO into SR model training with RefReward-SR as the core reward signal for preference-aligned generation. Extensive experiments show that our framework achieves substantially better alignment with human judgments, producing reconstructions that preserve semantic consistency while enhancing perceptual plausibility and visual naturalness. Code, models, and datasets will be released upon paper acceptance.

cs.CV↗

arXiv2026

FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation

Autoregressive models for 3D mesh generation suffer from a fundamental limitation: they flatten meshes into long vertex-coordinate sequences. This results in prohibitive computational costs, hindering the efficient synthesis of high-fidelity geometry. We argue this bottleneck stems from operating at the wrong semantic level. We introduce FACE, a novel Autoregressive Autoencoder (ARAE) framework that reconceptualizes the task by generating meshes at the face level. Our one-face-one-token strategy treats each triangle face, the fundamental building block of a mesh, as a single, unified token. This simple yet powerful design reduces the sequence length by a factor of nine, leading to an unprecedented compression ratio of 0.11, halving the previous state-of-the-art. This dramatic efficiency gain does not compromise quality; by pairing our face-level decoder with a powerful VecSet encoder, FACE achieves state-of-the-art reconstruction quality on standard benchmarks. The versatility of the learned latent space is further demonstrated by training a latent diffusion model that achieves high-fidelity, single-image-to-mesh generation. FACE provides a simple, scalable, and powerful paradigm that lowers the barrier to high-quality structured 3D content creation.

cs.CV↗

arXiv2025

BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch

Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design. The intricate coupling between geometric and topological elements in B-rep structures has forced existing generative methods to rely on cascaded multi-stage networks, resulting in error accumulation and computational inefficiency. We present BrepGPT, a single-stage autoregressive framework for B-rep generation. Our key innovation lies in the Voronoi Half-Patch (VHP) representation, which decomposes B-reps into unified local units by assigning geometry to nearest half-edges and sampling their next pointers. Unlike hierarchical representations that require multiple distinct encodings for different structural levels, our VHP representation facilitates unifying geometric attributes and topological relations in a single, coherent format. We further leverage dual VQ-VAEs to encode both vertex topology and Voronoi Half-Patches into vertex-based tokens, achieving a more compact sequential encoding. A decoder-only Transformer is then trained to autoregressively predict these tokens, which are subsequently mapped to vertex-based features and decoded into complete B-rep models. Experiments demonstrate that BrepGPT achieves state-of-the-art performance in unconditional B-rep generation. The framework also exhibits versatility in various applications, including conditional generation from category labels, point clouds, text descriptions, and images, as well as B-rep autocompletion and interpolation.

cs.CV↗

arXiv2025

CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection

With the rapid advancement of AI generative models, the visual quality of AI-generated images (AIIs) has become increasingly close to natural images, which inevitably raises security concerns. Most AII detectors often employ the conventional image classification pipeline with natural images and AIIs (generated by a generative model), which can result in limited detection performance for AIIs from unseen generative models. To solve this, we proposed a universal AI-generated image detector from the perspective of anomaly detection. Our discriminator does not need to access any AIIs and learn a generalizable representation with unsupervised learning. Specifically, we use the pre-trained CLIP encoder as the feature extractor and design a normalizing flow-like unsupervised model. Instead of AIIs, proxy images, e.g., obtained by applying a spectral modification operation on natural images, are used for training. Our models are trained by minimizing the likelihood of proxy images, optionally combined with maximizing the likelihood of natural images. Extensive experiments demonstrate the effectiveness of our method on AIIs produced by various image generators.

cs.CV↗

arXiv2025

iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generation

This paper propose iFlame, a novel transformer-based network architecture for mesh generation. While attention-based models have demonstrated remarkable performance in mesh generation, their quadratic computational complexity limits scalability, particularly for high-resolution 3D data. Conversely, linear attention mechanisms offer lower computational costs but often struggle to capture long-range dependencies, resulting in suboptimal outcomes. To address this trade-off, we propose an interleaving autoregressive mesh generation framework that combines the efficiency of linear attention with the expressive power of full attention mechanisms. To further enhance efficiency and leverage the inherent structure of mesh representations, we integrate this interleaving approach into an hourglass architecture, which significantly boosts efficiency. Our approach reduces training time while achieving performance comparable to pure attention-based models. To improve inference efficiency, we implemented a caching algorithm that almost doubles the speed and reduces the KV cache size by seven-eighths compared to the original Transformer. We evaluate our framework on ShapeNet and Objaverse, demonstrating its ability to generate high-quality 3D meshes efficiently. Our results indicate that the proposed interleaving framework effectively balances computational efficiency and generative performance, making it a practical solution for mesh generation. The training takes only 2 days with 4 GPUs on 39k data with a maximum of 4k faces on Objaverse.

cs.CV↗

arXiv2024

GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expression

Audio-driven talking head generation necessitates seamless integration of audio and visual data amidst the challenges posed by diverse input portraits and intricate correlations between audio and facial motions. In response, we propose a robust framework GoHD designed to produce highly realistic, expressive, and controllable portrait videos from any reference identity with any motion. GoHD innovates with three key modules: Firstly, an animation module utilizing latent navigation is introduced to improve the generalization ability across unseen input styles. This module achieves high disentanglement of motion and identity, and it also incorporates gaze orientation to rectify unnatural eye movements that were previously overlooked. Secondly, a conformer-structured conditional diffusion model is designed to guarantee head poses that are aware of prosody. Thirdly, to estimate lip-synchronized and realistic expressions from the input audio within limited training data, a two-stage training strategy is devised to decouple frequent and frame-wise lip motion distillation from the generation of other more temporally dependent but less audio-related motions, e.g., blinks and frowns. Extensive experiments validate GoHD's advanced generalization capabilities, demonstrating its effectiveness in generating realistic talking face results on arbitrary subjects.

cs.CV↗

arXiv2024

PointCFormer: a Relation-based Progressive Feature Extraction Network for Point Cloud Completion

Point cloud completion aims to reconstruct the complete 3D shape from incomplete point clouds, and it is crucial for tasks such as 3D object detection and segmentation. Despite the continuous advances in point cloud analysis techniques, feature extraction methods are still confronted with apparent limitations. The sparse sampling of point clouds, used as inputs in most methods, often results in a certain loss of global structure information. Meanwhile, traditional local feature extraction methods usually struggle to capture the intricate geometric details. To overcome these drawbacks, we introduce PointCFormer, a transformer framework optimized for robust global retention and precise local detail capture in point cloud completion. This framework embraces several key advantages. First, we propose a relation-based local feature extraction method to perceive local delicate geometry characteristics. This approach establishes a fine-grained relationship metric between the target point and its k-nearest neighbors, quantifying each neighboring point's contribution to the target point's local features. Secondly, we introduce a progressive feature extractor that integrates our local feature perception method with self-attention. Starting with a denser sampling of points as input, it iteratively queries long-distance global dependencies and local neighborhood relationships. This extractor maintains enhanced global structure and refined local details, without generating substantial computational overhead. Additionally, we develop a correction module after generating point proxies in the latent space to reintroduce denser information from the input points, enhancing the representation capability of the point proxies. PointCFormer demonstrates state-of-the-art performance on several widely used benchmarks. Our code is available at https://github.com/Zyyyyy0926/PointCFormer_Plus_Pytorch.

cs.CV↗

arXiv2024

OCMG-Net: Neural Oriented Normal Refinement for Unstructured Point Clouds

We present a robust refinement method for estimating oriented normals from unstructured point clouds. In contrast to previous approaches that either suffer from high computational complexity or fail to achieve desirable accuracy, our novel framework incorporates sign orientation and data augmentation in the feature space to refine the initial oriented normals, striking a balance between efficiency and accuracy. To address the issue of noise-caused direction inconsistency existing in previous approaches, we introduce a new metric called the Chamfer Normal Distance, which faithfully minimizes the estimation error by correcting the annotated normal with the closest point found on the potentially clean point cloud. This metric not only tackles the challenge but also aids in network training and significantly enhances network robustness against noise. Moreover, we propose an innovative dual-parallel architecture that integrates Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion, which enables the network to capture intricate geometric details more effectively and notably reduces ambiguity in scale selection. Extensive experiments demonstrate the superiority and versatility of our method in both unoriented and oriented normal estimation tasks across synthetic and real-world datasets among indoor and outdoor scenarios. The code is available at https://github.com/YingruiWoo/OCMG-Net.git.

cs.CV↗

arXiv2024

E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network

Point cloud normal estimation is a fundamental task in 3D geometry processing. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This results in inefficient learning of symmetric patterns. To address this issue, we propose E3-Net to achieve equivariance for normal estimation. We introduce an efficient random frame method, which significantly reduces the training resources required for this task to just 1/8 of previous work and improves the accuracy. Further, we design a Gaussian-weighted loss function and a receptive-aware inference strategy that effectively utilizes the local properties of point clouds. Our method achieves superior results on both synthetic and real-world datasets, and outperforms current state-of-the-art techniques by a substantial margin. We improve RMSE by 4% on the PCPNet dataset, 2.67% on the SceneNN dataset, and 2.44% on the FamousShape dataset.

cs.CV↗

arXiv2024

TCAN: Text-oriented Cross Attention Network for Multimodal Sentiment Analysis

Multimodal Sentiment Analysis (MSA) endeavors to understand human sentiment by leveraging language, visual, and acoustic modalities. Despite the remarkable performance exhibited by previous MSA approaches, the presence of inherent multimodal heterogeneities poses a challenge, with the contribution of different modalities varying considerably. Past research predominantly focused on improving representation learning techniques and feature fusion strategies. However, many of these efforts overlooked the variation in semantic richness among different modalities, treating each modality uniformly. This approach may lead to underestimating the significance of strong modalities while overemphasizing the importance of weak ones. Motivated by these insights, we introduce a Text-oriented Cross-Attention Network (TCAN), emphasizing the predominant role of the text modality in MSA. Specifically, for each multimodal sample, by taking unaligned sequences of the three modalities as inputs, we initially allocate the extracted unimodal features into a visual-text and an acoustic-text pair. Subsequently, we implement self-attention on the text modality and apply text-queried cross-attention to the visual and acoustic modalities. To mitigate the influence of noise signals and redundant features, we incorporate a gated control mechanism into the framework. Additionally, we introduce unimodal joint learning to gain a deeper understanding of homogeneous emotional tendencies across diverse modalities through backpropagation. Experimental results demonstrate that TCAN consistently outperforms state-of-the-art MSA methods on two datasets (CMU-MOSI and CMU-MOSEI).

cs.MM↗

arXiv2024

Deep Learning-based Image and Video Inpainting: A Survey

Image and video inpainting is a classic problem in computer vision and computer graphics, aiming to fill in the plausible and realistic content in the missing areas of images and videos. With the advance of deep learning, this problem has achieved significant progress recently. The goal of this paper is to comprehensively review the deep learning-based methods for image and video inpainting. Specifically, we sort existing methods into different categories from the perspective of their high-level inpainting pipeline, present different deep learning architectures, including CNN, VAE, GAN, diffusion models, etc., and summarize techniques for module design. We review the training objectives and the common benchmark datasets. We present evaluation metrics for low-level pixel and high-level perceptional similarity, conduct a performance evaluation, and discuss the strengths and weaknesses of representative inpainting methods. We also discuss related real-world applications. Finally, we discuss open challenges and suggest potential future research directions.

cs.CV↗

arXiv2023

CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-scale Geometry

This work presents an accurate and robust method for estimating normals from point clouds. In contrast to predecessor approaches that minimize the deviations between the annotated and the predicted normals directly, leading to direction inconsistency, we first propose a new metric termed Chamfer Normal Distance to address this issue. This not only mitigates the challenge but also facilitates network training and substantially enhances the network robustness against noise. Subsequently, we devise an innovative architecture that encompasses Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion. This design empowers the network to capture intricate geometric details more effectively and alleviate the ambiguity in scale selection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on both synthetic and real-world datasets, particularly in scenarios contaminated by noise. Our implementation is available at https://github.com/YingruiWoo/CMG-Net_Pytorch.

cs.CV↗

arXiv2023

DPE: Disentanglement of Pose and Expression for General Video Portrait Editing

One-shot video-driven talking face generation aims at producing a synthetic talking video by transferring the facial motion from a video to an arbitrary portrait image. Head pose and facial expression are always entangled in facial motion and transferred simultaneously. However, the entanglement sets up a barrier for these methods to be used in video portrait editing directly, where it may require to modify the expression only while maintaining the pose unchanged. One challenge of decoupling pose and expression is the lack of paired data, such as the same pose but different expressions. Only a few methods attempt to tackle this challenge with the feat of 3D Morphable Models (3DMMs) for explicit disentanglement. But 3DMMs are not accurate enough to capture facial details due to the limited number of Blenshapes, which has side effects on motion transfer. In this paper, we introduce a novel self-supervised disentanglement framework to decouple pose and expression without 3DMMs and paired data, which consists of a motion editing module, a pose generator, and an expression generator. The editing module projects faces into a latent space where pose motion and expression motion can be disentangled, and the pose or expression transfer can be performed in the latent space conveniently via addition. The two generators render the modified latent codes to images, respectively. Moreover, to guarantee the disentanglement, we propose a bidirectional cyclic training strategy with well-designed constraints. Evaluations demonstrate our method can control pose or expression independently and be used for general video editing.

cs.CV↗

arXiv2022

M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval

Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale pre-trained model CLIP for TVR do not focus on multi-modal cues in videos. Furthermore, the traditional methods simply concatenating multi-modal features do not exploit fine-grained cross-modal information in videos. In this paper, we propose a multi-level multi-modal hybrid fusion (M2HF) network to explore comprehensive interactions between text queries and each modality content in videos. Specifically, M2HF first utilizes visual features extracted by CLIP to early fuse with audio and motion features extracted from videos, obtaining audio-visual fusion features and motion-visual fusion features respectively. Multi-modal alignment problem is also considered in this process. Then, visual features, audio-visual fusion features, motion-visual fusion features, and texts extracted from videos establish cross-modal relationships with caption queries in a multi-level way. Finally, the retrieval outputs from all levels are late fused to obtain final text-video retrieval results. Our framework provides two kinds of training strategies, including an ensemble manner and an end-to-end manner. Moreover, a novel multi-modal balance loss function is proposed to balance the contributions of each modality for efficient end-to-end training. M2HF allows us to obtain state-of-the-art results on various benchmarks, eg, Rank@1 of 64.9\%, 68.2\%, 33.2\%, 57.1\%, 57.8\% on MSR-VTT, MSVD, LSMDC, DiDeMo, and ActivityNet, respectively.

cs.MM↗