Related papers: CVD-STORM: Cross-View Video Diffusion with Spatial…
Forecasting a typical object's future motion is a critical task for interpreting and interacting with dynamic environments in computer vision. Event-based sensors, which could capture changes in the scene with exceptional temporal…
We present Fashion-VDM, a video diffusion model (VDM) for generating virtual try-on videos. Given an input garment image and person video, our method aims to generate a high-quality try-on video of the person wearing the given garment,…
We present STORM (Search-Guided Generative World Models), a novel framework for spatio-temporal reasoning in robotic manipulation that unifies diffusion-based action generation, conditional video prediction, and search-based planning.…
Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically, the sampling distribution is hand-crafted (e.g a Gaussian, or a grid). Recently,…
While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of…
Recent video generative models have demonstrated impressive visual fidelity, yet they often struggle with semantic, geometric, and identity consistency. In this paper, we propose a system-level framework, termed the Divide-and-Conquer…
High dynamic range (HDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects…
This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings,…
Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes into a COmpact set of 1D latent vectors without sacrificing…
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…
Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small…
In recent years there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera controllability of generated frames have remained unsolved. Recent studies have attempted to incorporate camera…
Camera sensor simulation serves as a critical role for autonomous driving (AD), e.g. evaluating vision-based AD algorithms. While existing approaches have leveraged generative models for controllable image/video generation, they remain…
Portrait animation aims to generate photo-realistic videos from a single source image by reenacting the expression and pose from a driving video. While early methods relied on 3D morphable models or feature warping techniques, they often…
Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…
Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific…
Given the high complexity of directly generating high-dimensional data such as 4D, we present 4DVD, a cascaded video diffusion model that generates 4D content in a decoupled manner. Unlike previous multi-view video methods that directly…
We introduce LTX-Video, a transformer-based latent diffusion model that adopts a holistic approach to video generation by seamlessly integrating the responsibilities of the Video-VAE and the denoising transformer. Unlike existing methods,…
Recent video generation models largely rely on video autoencoders that compress pixel-space videos into latent representations. However, existing video autoencoders suffer from three major limitations: (1) fixed-rate compression that wastes…
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video…