Related papers: Controllable Weather Synthesis and Removal with Vi…
Long video generation remains a challenging and compelling topic in computer vision. Diffusion based models, among the various approaches to video generation, have achieved state of the art quality with their iterative denoising procedures.…
Although prevailing camera-controlled video generation models can produce cinematic results, lifting them directly to the generation of 3D-consistent and high-fidelity time-synchronized multi-view videos remains challenging, which is a…
Recent advancements in diffusion-based models have demonstrated significant success in generating images from text. However, video editing models have not yet reached the same level of visual quality and user control. To address this, we…
Image tiling -- the seamless connection of disparate images to create a coherent visual field -- is crucial for applications such as texture creation, video game asset development, and digital art. Traditionally, tiles have been constructed…
Data scarcity is a primary obstacle in developing robust Machine Learning (ML) models for detecting rapidly intensifying tropical cyclones. Traditional data augmentation techniques (rotation, flipping, brightness adjustment) fail to…
Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they tend to be object centric and struggle with complex and…
Tropical cyclone (TC) forecasting is crucial for disaster preparedness and mitigation. While recent deep learning approaches have shown promise, existing methods often treat TC evolution as a series of independent frame-to-frame…
Scene text detection techniques have garnered significant attention due to their wide-ranging applications. However, existing methods have a high demand for training data, and obtaining accurate human annotations is labor-intensive and…
Generating videos with realistic and physically plausible motion is one of the main recent challenges in computer vision. While diffusion models are achieving compelling results in image generation, video diffusion models are limited by…
This study seeks to automate camera movement control for filming existing subjects into attractive videos, contrasting with the creation of non-existent content by directly generating the pixels. We select drone videos as our test case due…
Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with…
Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time…
Despite remarkable progress having been made on the problem of 3D human pose and shape estimation (HPS), current state-of-the-art methods rely heavily on either confined indoor mocap datasets or datasets generated by a rendering engine…
Advancements in 3D scene reconstruction have transformed 2D images from the real world into 3D models, producing realistic 3D results from hundreds of input photos. Despite great success in dense-view reconstruction scenarios, rendering a…
We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models. Given a text prompt, Imagen Video generates high definition videos using a base video generation model and a sequence of…
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…
Diffusion models exhibited tremendous progress in image and video generation, exceeding GANs in quality and diversity. However, they are usually trained on very large datasets and are not naturally adapted to manipulate a given input image…
Multi-modal 3D object detection is important for reliable perception in robotics and autonomous driving. However, its effectiveness remains limited under adverse weather conditions due to weather-induced distortions and misalignment between…
Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external…
Earth System Models (ESMs) are essential for understanding the interaction between human activities and the Earth's climate. However, the computational demands of ESMs often limit the number of simulations that can be run, hindering the…