Related papers: X-Mesh: Towards Fast and Accurate Text-driven 3D S…

Autonomous cars need geometric accuracy and semantic understanding to navigate complex environments, yet most stacks handle them separately. We present XYZ-Drive, a single vision-language model that reads a front-camera frame, a 25m…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly…

Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges…

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…

The recent GAN inversion methods have been able to successfully invert the real image input to the corresponding editable latent code in StyleGAN. By combining with the language-vision model (CLIP), some text-driven image manipulation…

We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when…

Interpretable driver attention prediction is crucial for human-like autonomous driving. However, existing datasets provide only scene-level global gaze rather than fine-grained object-level annotations, inherently failing to support…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

In the realm of Text-Based Person Search (TBPS), mainstream methods aim to explore more efficient interaction frameworks between text descriptions and visual data. However, recent approaches encounter two principal challenges. Firstly, the…

Large vision language models (LVLMs) have demonstrated impressive performance across a wide range of tasks. These capabilities largely stem from visual instruction tuning, which fine-tunes models on datasets consisting of curated…

Mesh deformation is a fundamental tool in 3D content manipulation. Despite extensive prior research, existing approaches often suffer from low output quality, require significant manual tuning, or depend on data-intensive training. To…

In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler). We aim at stylizing any 3D scene with an arbitrary style from a text description, and synthesizing the novel stylized view, which is…

Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anything Model (SAM) and its high-quality variant SAM-HQ. These…

Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse…

While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the complexities of multi-view consistency and spatial control.…

Portrait stylization is a long-standing task enabling extensive applications. Although 2D-based methods have made great progress in recent years, real-world applications such as metaverse and games often demand 3D content. On the other…

Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks. While existing methods appropriately model channel-, spatial- and self-attention, they primarily…

Text-guided diffusion models have significantly advanced image editing, enabling highly realistic and local modifications based on textual prompts. While these developments expand creative possibilities, their malicious use poses…

We introduce Amortized Text-to-Mesh (AToM), a feed-forward text-to-mesh framework optimized across multiple text prompts simultaneously. In contrast to existing text-to-3D methods that often entail time-consuming per-prompt optimization and…