Related papers: V-Co: A Closer Look at Visual Representation Align…
Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing…
Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive…
The synergy between generative and discriminative models receives growing attention. While discriminative Contrastive Language-Image Pre-Training (CLIP) excels in high-level semantics, it struggles with perceiving fine-grained visual…
Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently…
Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between…
Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during…
Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling. A diffusion model is a deep generative model that is based on two stages, a forward…
We study the use of deep features extracted from a pretrained Vision Transformer (ViT) as dense visual descriptors. We observe and empirically demonstrate that such features, when extractedfrom a self-supervised ViT model (DINO-ViT),…
Diffusion models have achieved remarkable advancements in text-to-image generation. However, existing models still have many difficulties when faced with multiple-object compositional generation. In this paper, we propose RealCompo, a new…
Image demosaicing and denoising play a critical role in the raw imaging pipeline. These processes have often been treated as independent, without considering their interactions. Indeed, most classic denoising methods handle noisy RGB…
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…
In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a…
Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA…
Image forgery localization aims to precisely identify tampered regions within images, but it commonly depends on costly pixel-level annotations. To alleviate this annotation burden, weakly supervised image forgery localization (WSIFL) has…
Many real-world applications involve data from multiple modalities and thus exhibit the view heterogeneity. For example, user modeling on social media might leverage both the topology of the underlying social network and the content of the…
Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…
Early detection through imaging and accurate diagnosis is crucial in mitigating the high mortality rate associated with breast cancer. However, locating tumors from low-resolution and high-noise medical images is extremely challenging.…
Predicting drug-target affinity is fundamental to virtual screening and lead optimization. However, existing deep models often suffer from representation collapse in stringent cold-start regimes, where the scarcity of labels and domain…
Recent advancements in text-to-image generative models have demonstrated a remarkable ability to capture a deep semantic understanding of images. In this work, we leverage this semantic knowledge to transfer the visual appearance between…
Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For…