Related papers: CountLoop: Training-Free High-Instance Image Gener…
Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often struggles with generalization, composability, and robustness against reward hacking. Recent studies have explored prompt refinement as a…
This paper tackles the problem of object counting in images. Existing approaches rely on extensive training data with point annotations for each object, making data collection labor-intensive and time-consuming. To overcome this, we propose…
Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, named CrowdCLIP. The…
Recent advances in conditional generative image models have enabled impressive results. On the one hand, text-based conditional models have achieved remarkable generation quality, by leveraging large-scale datasets of image-text pairs. To…
Zero-shot object counting aims to count instances of arbitrary object categories specified by text descriptions. Existing methods typically rely on vision-language models like CLIP, but often exhibit limited sensitivity to text prompts. We…
Controllable image generation has always been one of the core demands in image generation, aiming to create images that are both creative and logical while satisfying additional specified conditions. In the post-AIGC era, controllable…
Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…
Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only supervision. We introduce InstAP, an Instance-Aware Pre-training framework that jointly…
This paper proposes a novel framework for multi-label image recognition without any training data, called data-free framework, which uses knowledge of pre-trained Large Language Model (LLM) to learn prompts to adapt pretrained…
Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further…
In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes.…
The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing,…
Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions. In this paper, we…
Layout-to-Image generation aims to create complex scenes with precise control over the placement and arrangement of subjects. Existing works have demonstrated that pre-trained Text-to-Image diffusion models can achieve this goal without…
Recently, GAN inversion methods combined with Contrastive Language-Image Pretraining (CLIP) enables zero-shot image manipulation guided by text prompts. However, their applications to diverse real images are still difficult due to the…
Image composition targets at synthesizing a realistic composite image from a pair of foreground and background images. Recently, generative composition methods are built on large pretrained diffusion models to generate composite images,…
Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…
Text-to-image diffusion models enable high-quality image generation but are computationally expensive. While prior work optimizes per-inference efficiency, we explore an orthogonal approach: reducing redundancy across correlated prompts.…
Diffusion models can generate realistic and diverse images, potentially facilitating data availability for data-intensive perception tasks. However, leveraging these models to boost performance on downstream tasks with synthetic data poses…
We introduce a novel, training-free system for reconstructing, understanding, and rendering 3D indoor scenes from a sparse set of unposed RGB images. Unlike traditional radiance field approaches that require dense views and per-scene…