Related papers: From Slow Bidirectional to Fast Autoregressive Vid…
Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas…
Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based…
Video diffusion models have recently achieved remarkable results in video generation. Despite their encouraging performance, most of these models are mainly designed and trained for short video generation, leading to challenges in…
Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…
Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose…
We introduce Reangle-A-Video, a unified framework for generating synchronized multi-view videos from a single input video. Unlike mainstream approaches that train multi-view video diffusion models on large-scale 4D datasets, our method…
Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious…
Score-based distillation methods (e.g., variational score distillation) train one-step diffusion models by first pre-training a teacher score model and then distilling it into a one-step student model. However, the gradient estimator in the…
Video generation has drawn significant interest recently, pushing the development of large-scale models capable of producing realistic videos with coherent motion. Due to memory constraints, these models typically generate short video…
Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation…
Interactive motion synthesis is essential in creating immersive experiences in entertainment applications, such as video games and virtual reality. However, generating animations that are both high-quality and contextually responsive…
Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods…
While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as novel structural constraints or latest user preferences --…
Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is…
Recent advancements in diffusion-based video generation have produced impressive and high-fidelity short videos. To extend these successes to generate coherent long videos, most video diffusion models (VDMs) generate videos in an…
Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are typically built upon multi-step frameworks like diffusion and…
The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…
Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updates. We introduce W-Flow, a framework for training a…
Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…
Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapted from image-based techniques, lack a single-step…