相关论文: DynamicScaler: Seamless and Scalable Video Generat…
Video generation powers a vast array of downstream applications. However, while the de facto standard, i.e., latent diffusion models, typically employ heavily conditioned denoising networks, their decoders often remain unconditional. We…
When interactively exploring video data, video-native querying involves consuming query results as videos, including steps such as compilation of extracted video clips or data overlays. These video-native queries are bottlenecked by…
Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce \textbf{AnyView}, a…
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a…
Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While recent approaches have…
The convergence of 3D geometric perception and video synthesis has created an unprecedented demand for large-scale video data that is rich in both semantic and spatio-temporal information. While existing datasets have advanced either 3D…
We present a differentiable volume rendering solution that provides differentiability of all continuous parameters of the volume rendering process. This differentiable renderer is used to steer the parameters towards a setting with an…
Many compelling video processing effects can be achieved if per-pixel depth information and 3D camera calibrations are known. However, the success of such methods is highly dependent on the accuracy of this "scene-space" information. We…
This paper presents a novel end-to-end dynamic time-lapse video generation framework, named DTVNet, to generate diversified time-lapse videos from a single landscape image conditioned on normalized motion vectors. The proposed DTVNet…
We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM reconstructions that treat moving objects as outliers. We…
Pansharpening aims to generate high-resolution multi-spectral images by fusing the spatial detail of panchromatic images with the spectral richness of low-resolution MS data. However, most existing methods are evaluated under limited,…
Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation. By inverting such renderer, one can think of a learning approach to infer 3D information from 2D images. However, standard…
In this work, we rethink the approach to video super-resolution by introducing a method based on the Diffusion Posterior Sampling framework, combined with an unconditional video diffusion transformer operating in latent space. The video…
Our work tackles the fundamental challenge of image segmentation in computer vision, which is crucial for diverse applications. While supervised methods demonstrate proficiency, their reliance on extensive pixel-level annotations limits…
We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models. Our key…
The synthesis of spatiotemporally coherent 4D content presents fundamental challenges in computer vision, requiring simultaneous modeling of high-fidelity spatial representations and physically plausible temporal dynamics. Current…
Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability…
Diffusion-based video super-resolution (VSR) methods deliver strong perceptual quality but are often unsuitable for latency-sensitive scenarios due to reliance on future frames and expensive multi-step denoising. We propose Stream-DiffVSR,…
Generating coherent and useful image/video scenes from a free-form textual description is technically a very difficult problem to handle. Textual description of the same scene can vary greatly from person to person, or sometimes even for…
Diffusion-based image-to-video (I2V) models are increasingly effective, yet they struggle to scale to ultra-high-resolution inputs (e.g., 4K). Generating videos at the model's native resolution often loses fine-grained structure, whereas…