Related papers: Debiasing Diffusion Priors via 3D Attention for Co…

Diffusion models have demonstrated remarkable performance in image generation, particularly within the domain of style transfer. Prevailing style transfer approaches typically leverage pre-trained diffusion models' robust feature extraction…

Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient…

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language…

Large-scale diffusion models have made significant advances in image generation, particularly through cross-attention mechanisms. While cross-attention has been well-studied in text-to-image tasks, their interpretability in image-to-image…

Understanding 4D point cloud videos is essential for enabling intelligent agents to perceive dynamic environments. However, temporal scale bias across varying frame rates and distributional uncertainty in irregular point clouds make it…

It is inherently ambiguous to lift 2D results from pre-trained diffusion models to a 3D world for text-to-3D generation. 2D diffusion models solely learn view-agnostic priors and thus lack 3D knowledge during the lifting, leading to the…

Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images. However, these models often face significant computational bottlenecks, particularly in…

High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…

The growing demand for customized visual content has led to the rise of personalized text-to-image (T2I) diffusion models. Despite their remarkable potential, they pose significant privacy risk when misused for malicious purposes. In this…

Modality differences have led to the development of heterogeneous architectures for vision and language models. While images typically require 2D non-causal modeling, texts utilize 1D causal modeling. This distinction poses significant…

We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models…

Diffusion-based text-to-image models have rapidly gained popularity for their ability to generate detailed and realistic images from textual descriptions. However, these models often reflect the biases present in their training data,…

Recently, text-to-image generation with diffusion models has made significant advancements in both higher fidelity and generalization capabilities compared to previous baselines. However, generating holistic multi-view consistent images…

While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches…

Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global scene coherence and…

Recent diffusion-based Single-image 3D portrait generation methods typically employ 2D diffusion models to provide multi-view knowledge, which is then distilled into 3D representations. However, these methods usually struggle to produce…

Accurate beam prediction is essential for maintaining reliable links and high spectral efficiency in dynamic low-altitude wireless networks. However, existing approaches often fail to capture the deep correlations across heterogeneous…

Text-guided domain adaptation and generation of 3D-aware portraits find many applications in various fields. However, due to the lack of training data and the challenges in handling the high variety of geometry and appearance, the existing…

Open-Vocabulary Temporal Action Detection (OV-TAD) aims to localize and classify action segments of unseen categories in untrimmed videos, where effective alignment between action semantics and video representations is critical for accurate…

Recent advancements in 3D Gaussian Splatting (3D-GS) enable high-quality 3D scene reconstruction from RGB images. Many studies extend this paradigm for language-driven open-vocabulary scene understanding. However, most of them simply…