相关论文: Boosting Resolution Generalization of Diffusion Tr…

Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel state information (CSI) modeling, latent characterization, and task-specific prediction.…

Image restoration problems are typical ill-posed problems where the regularization term plays an important role. The regularization term learned via generative approaches is easy to transfer to various image restoration, but offers inferior…

Diffusion models have achieved remarkable success, yet their training remains inefficient due to a severe optimization bottleneck, which we term Representation Degradation. As noise levels increase, the outputs of the trained model exhibit…

Auto-regressive neural sequence models have been shown to be effective across text generation tasks. However, their left-to-right decoding order prevents generation from being parallelized. Insertion Transformer (Stern et al., 2019) is an…

Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet by training in high-dimensional semantic latent spaces. In this work, we investigate whether this framework can scale to large-scale,…

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

Rotary Position Embedding (RoPE) performs remarkably on language models, especially for length extrapolation of Transformers. However, the impacts of RoPE on computer vision domains have been underexplored, even though RoPE appears capable…

Transformers have recently been shown to generate high quality images from text input. However, the existing method of pose conditioning using skeleton image tokens is computationally inefficient and generate low quality images. Therefore…

Generating 3D images of complex objects conditionally from a few 2D views is a difficult synthesis problem, compounded by issues such as domain gap and geometric misalignment. For instance, a unified framework such as Generative Adversarial…

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works…

We present RePOSE, a fast iterative refinement method for 6D object pose estimation. Prior methods perform refinement by feeding zoomed-in input and rendered RGB images into a CNN and directly regressing an update of a refined pose. Their…

Previous text-to-image diffusion models typically employ supervised fine-tuning (SFT) to enhance pre-trained base models. However, this approach primarily minimizes the loss of mean squared error (MSE) at the pixel level, neglecting the…

Diffusionmodels(DMs)havedemonstratedremarkableachievements in synthesizing images of high fidelity and diversity. However, the extensive computational requirements and slow generative speed of diffusion models have limited their widespread…

High-dynamic-range (HDR) formats and displays are becoming increasingly prevalent, yet state-of-the-art image generators (e.g., Stable Diffusion and FLUX) typically remain limited to low-dynamic-range (LDR) output due to the lack of…

The enduring inability of image generative models to recreate intricate geometric features, such as those present in human hands and fingers has been an ongoing problem in image generation for nearly a decade. While strides have been made…

Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are…

Diffusion reconstruction plays a critical role in various applications such as image editing, restoration, and style transfer. In theory, the reconstruction should be simple - it just inverts and regenerates images by numerically solving…

Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, yet their $\mathcal{O}(L^2)$ attention complexity poses a formidable bottleneck for long-sequence synthesis. While recent sparse-linear attention hybrids aim…

Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different…