39 accepted papers
Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and actions remain underexplored, especially for general-purpose s…
Resolution generalization in image generation tasks enables the production of higher-resolution images with lower training resolution overhead. However, a key obstacle for diffusion transformers in addressing this problem is the mismatch between positional encodings seen at inference and those used
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and \textbf{\textit{reasoning}}. Despite recent advances of T2I models…
Video autoregressive generation (VideoAR) sequentially predicts future frames conditioned on history frames. Despite the advance of recent diffusion-based VideoAR, the role of conditioning signal—internal representations of history frames—remains underexplored. Inspired by the success of strong cond…
Existing denoising generative models rely on solving discretized reverse-time SDEs or ODEs. In this paper, we identify a long-overlooked yet pervasive issue in this family of models: a misalignment between the pre-defined noise level and the actual noise level encoded in intermediate states during s…
The demand for high-resolution video generation is growing rapidly. However, the generation resolution is severely constrained by slow inference speeds. For instance, Wan2.1 requires over 50 minutes to generate a single 720p video. While previous works explore accelerating video generation from vari
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we identify 1) a *high-variance regime* near the prior, where optimization is c…
Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and limited modal diversity for comprehensive world knowledge represe
The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiTs can be naturally represented by the Monarch matrix. It is a class of structure
While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to convey through language alone (e.g., imagine teaching someone
Text-to-video (T2V) generative models have rapidly advanced and found widespread applications across fields like entertainment, education, and marketing. However, the adversarial vulnerabilities of these models remain rarely explored. We observe that in T2V generation tasks, the generated videos oft…
Recent advancements in video diffusion models enable the generation of photorealistic videos with impressive 3D consistency and temporal coherence. However, the extent to which these AI-generated videos simulate the 3D visual world remains underexplored. In this paper, we introduce Learned 3D Evalua…
In visual generation tasks, the responses and combinations of complex concepts often lack stability and are error-prone, which remains an under-explored area. In this paper, we attempt to explore the causal factors for poor concept responses through elaborately designed experiments. We also design a…
With the continuous progress of visual generation technologies, the scale of video datasets has grown exponentially. The quality of these datasets plays a pivotal role in the performance of video generation models. We assert that temporal splitting, detailed captions, and video quality filtering are…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual inputs, yet modality alignment remains one of the most challenging aspects. Current MLLMs typically rely on simple adapter architectures and pretraining approaches to bridge vision en
Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accurate contextualization and structural control. So t…
The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to casual prompts, this paper presents the first comprehensive analysis on SAM’s segmentation stability across a diverse sp…
Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters before large-scale training. While scaling laws are employed in…
Despite the remarkable generation quality of video Diffusion Transformer (DiT) models, their practical deployment is severely hindered by extensive computational requirements. This inefficiency stems from two key challenges: the quadratic complexity of self-attention with respect to token length and…
Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the computational cost of the diffusion model to scale linearly w…
Previous methods for Video Frame Interpolation (VFI) have encountered challenges notably the manifestation of blur and ghosting effects. These issues can be traced back to two pivotal factors: unavoidable motion errors and misalignment in supervision. In practice motion estimates often prove to be e…
Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in object numbers. To address these limitations, we propose Video…
Videos stored on mobile devices or delivered on the Internet are usually in compressed format and are of various unknown compression parameters, but most video super-resolution (VSR) methods often assume ideal inputs resulting in large performance gap between experimental settings and real-world app…
Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the model complexity and might fail in case of occlusion or com…
Reference-based image super-resolution (RefSR) has shown promising success in recovering high-frequency details by utilizing an external reference image (Ref). In this task, texture details are transferred from the Ref image to the low-resolution (LR) image according to their point- or patch-wise co…
Video super-resolution (VSR) aims to utilize multiple low-resolution frames to generate a high-resolution prediction for each frame. In this process, inter- and intra-frames are the key sources for exploiting temporal and spatial information. However, there are a couple of limitations for existing V…
Unpaired image-to-image translation aims to translate images from the source class to target one by providing sufficient data for these classes. Current few-shot translation methods use multiple reference images to describe the target domain through extracting common features. In this paper, we focu…
Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image. Previous works assume missing region patterns are known, limiting its application scope. In this paper, we relax the assumption by defining a new blind inpainting setting, mak…
Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform. We in this paper propose the spontaneous motion estimation module, along with a refinement part, to learn attribute-driven deformation between…
Dynamic Scene deblurring is a challenging low-level vision task where spatially variant blur is caused by many factors, e.g., camera shake and object motion. Recent study has made significant progress. Compared with the parameter independence scheme [19] and parameter sharing scheme [33], we develop…
This paper studies the fundamental problem of extrapolating visual context using deep generative models, i.e., extending image borders with plausible structure and details. This seemingly easy task actually faces many crucial technical challenges and has its unique properties. The two major issues a…
Digital face manipulation has become a popular and fascinating way to touch images with the prevalence of smart phones and social networks. With a wide variety of user preferences, facial expressions, and accessories, a general and flexible model is necessary to accommodate different types of facial…
In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF r…
In single image deblurring, the ``coarse-to-fine'' scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and pro…
Previous CNN-based video super-resolution approaches need to align multiple frames to the reference. In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results. We accordingly propose a 'sub-pixel motion compensation' (SPMC) layer in a CN…
Estimating correspondence between two images and extracting the foreground object are two challenges in computer vision. With dual-lens smart phones, such as iPhone 7Plus and Huawei P9, coming into the market, two images of slightly different views provide us new information to unify the two topics.…
In this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters. We broadly define filters as operations to smooth images or to produce layers via global or local algorithms. And we raise the intriguingly problem if they are reservable to the…
Ubiquitous motion blur easily fails multi-frame super-resolution (MFSR). Our method proposed in this paper tackles this issue by optimally searching least blurred pixels in MFSR. An EM framework is proposed to guide residual blur estimation and high-resolution image reconstruction. To suppress noise…
We propose a new direction for fast video super-resolution (VideoSR) via a SR draft ensemble, which is defined as the set of high-resolution patch candidates before final image deconvolution. Our method contains two main components -- i.e., SR draft ensemble generation and its optimal reconstruction…