相关论文: Getting it Right: Improving Spatial Consistency in…

In recent years, Text-to-Image (T2I) models have been extensively studied, especially with the emergence of diffusion models that achieve state-of-the-art results on T2I synthesis tasks. However, existing benchmarks heavily rely on…

Spatial confounding poses a significant challenge in scientific studies involving spatial data, where unobserved spatial variables can influence both treatment and outcome, possibly leading to spurious associations. To address this problem,…

Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in…

The text to medical image (T2MedI) with latent diffusion model has great potential to alleviate the scarcity of medical imaging data and explore the underlying appearance distribution of lesions in a specific patient status description.…

The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between…

Zero-shot Image Captioning (ZIC) increasingly utilizes synthetic datasets generated by text-to-image (T2I) models to mitigate the need for costly manual annotation. However, these T2I models often produce images that exhibit semantic…

The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…

Traditionally, sparse retrieval systems relied on lexical representations to retrieve documents, such as BM25, dominated information retrieval tasks. With the onset of pre-trained transformer models such as BERT, neural sparse retrieval has…

Data augmentation has been recently leveraged as an effective regularizer in various vision-language deep neural networks. However, in text-to-image synthesis (T2Isyn), current augmentation wisdom still suffers from the semantic mismatch…

Image-to-text tasks, such as open-ended image captioning and controllable image description, have received extensive attention for decades. Here, we further advance this line of work by presenting Visual Spatial Description (VSD), a new…

Frame of Reference (FoR) is a fundamental concept in spatial reasoning that humans utilize to comprehend and describe space. With the rapid progress in Multimodal Language models, the moment has come to integrate this long-overlooked…

Many deep learning tasks require annotations that are too time consuming for human operators, resulting in small dataset sizes. This is especially true for dense regression problems such as crowd counting which requires the location of…

Current text-to-image (T2I) models often fail to account for diverse human experiences, leading to misaligned systems. We advocate for pluralistic alignment, where an AI understands and is steerable towards diverse, and often conflicting,…

Text-to-image (T2I) models have made substantial progress in generating images from textual prompts. However, they frequently fail to produce images consistent with physical commonsense, a vital capability for applications in world…

Image inpainting aims to fill missing pixels in damaged images and has achieved significant progress with cut-edging learning techniques. Nevertheless, state-of-the-art inpainting methods are mainly designed for nature images and cannot…

Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model's original generative capabilities. However, this process often leads to overfitting,…

Generative foundation models have advanced large-scale text-driven natural image generation, becoming a prominent research trend across various vertical domains. However, in the remote sensing field, there is still a lack of research on…

Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis. However, many existing systems rely on explicit modality switching,…

Reconstructing 3D scenes with high fidelity and efficiency remains a central pursuit in computer vision and graphics. Recent advances in 3D Gaussian Splatting (3DGS) enable photorealistic rendering with Gaussian primitives, yet the modeling…

Recent action recognition models have achieved impressive results by integrating objects, their locations and interactions. However, obtaining dense structured annotations for each frame is tedious and time-consuming, making these methods…