9 accepted papers
Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint optimization. To address these issues, we propose PixelDiT,
Ultra-high-resolution (UHR) text-to-image synthesis faces significant hurdles, including immense computational costs and a scarcity of training data. To address these, we introduce RealUHR, an efficient and scalable framework for generating photorealistic 4K images. At its core, RealUHR employs a Pa
Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges such as the intricate interplay of physical effects and insufficient paired training data. In this work, we introduce Omn…
Latent Diffusion Models (LDMs) have markedly advanced the quality of image inpainting and local editing. However, the inherent latent compression often introduces pixel-level inconsistencies, such as chromatic shifts, texture mismatches, and visible seams along editing boundaries. Existing remedies,…
Vanilla image completion approaches exhibit sensitivity to large missing regions, attributed to the limited availability of reference information for plausible generation. To mitigate this, existing methods incorporate the extra cue as guidance for image completion. Despite improvements, these appro…
Diffusion models equipped with language models demonstrate excellent controllability in image generation tasks, allowing image processing to adhere to human instructions. However, the lack of diverse instruction-following data hampers the development of models that effectively recognize and execute…
Learning to capture human motion is essential to 3D human pose and shape estimation from monocular video, which is widely used in many 3D applications. However, the existing methods mainly rely on recurrent or convolutional operation to model such temporal information, which limits the ability to ca…
"Image inpainting seeks a semantically consistent way to recover the corrupted image in the light of its unmasked content. Previous approaches usually reuse the well-trained GAN as effective prior to generate realistic patches for missing holes with GAN inversion. Nevertheless, the ignorance of hard…
"Image inpainting is an ill-posed problem to recover missing or damaged image content based on incomplete images with masks. Previous works usually predict the auxiliary structures (\eg, edges, segmentation and contours) to help fill visually realistic patches in a multi-stage fashion. However, impr…