Related papers: Seeing Clearly, Forgetting Deeply: Revisiting Fine…
Recent research on automotive driving developed an efficient end-to-end learning mode that directly maps visual input to control commands. However, it models distinct driving variations in a single network, which increases learning…
Text-to-video generation is expensive, so only a few samples are typically produced per prompt. In this low-sample regime, maximizing the value of each batch requires high cross-video diversity. Recent methods improve diversity for image…
Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To…
This paper offers a comprehensive analysis of recent advancements in video inpainting techniques, a critical subset of computer vision and artificial intelligence. As a process that restores or fills in missing or corrupted portions of…
Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion…
Generative models have made significant progress in synthesizing visual content, including images, videos, and 3D/4D structures. However, they are typically trained with surrogate objectives such as likelihood or reconstruction loss, which…
Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory modeling with video generation, leading to inconsistent…
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…
Camera control has been actively studied in text or image conditioned video generation tasks. However, altering camera trajectories of a given video remains under-explored, despite its importance in the field of video creation. It is…
Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and traditional simulation suffers from a persistent reality gap. While recent generative…
With the rapid advancement of autonomous driving technology, a lack of data has become a major obstacle to enhancing perception model accuracy. Researchers are now exploring controllable data generation using world models to diversify…
Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…
Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accurately modeling visual outcomes and state transitions over…
Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail…
Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control. However, they implicitly assume that the world only evolves within the observer's…
A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs),…
Generating videos for visual storytelling can be a tedious and complex process that typically requires either live-action filming or graphics animation rendering. To bypass these challenges, our key idea is to utilize the abundance of…
Data seems cheap to get, and in many ways it is, but the process of creating a high quality labeled dataset from a mass of data is time-consuming and expensive. With the advent of rich 3D repositories, photo-realistic rendering systems…
In this paper, we address the challenge of generating temporally consistent videos with motion guidance. While many existing methods depend on additional control modules or inference-time fine-tuning, recent studies suggest that effective…
There has been a recent explosion of impressive generative models that can produce high quality images (or videos) conditioned on text descriptions. However, all such approaches rely on conditional sentences that contain unambiguous…