Related papers: WorldReel: 4D Video Generation with Consistent Geo…
The field of generative models has recently witnessed significant progress, with diffusion models showing remarkable performance in image generation. In light of this success, there is a growing interest in exploring the application of…
Video diffusion models generate high-quality and diverse worlds; however, individual frames often lack 3D consistency across the output sequence, which makes the reconstruction of 3D worlds difficult. To this end, we propose a new method…
Closed-loop simulation is essential for advancing end-to-end autonomous driving systems. Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on conditions closely aligned with training data distributions, which…
We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame…
Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world model that bridges panoramic video generation with evolving…
Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a comprehensive comparison and analysis of limitations remains…
We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a…
We present a novel video generation framework that integrates 3-dimensional geometry and dynamic awareness. To achieve this, we augment 2D videos with 3D point trajectories and align them in pixel space. The resulting 3D-aware video…
Recent advancements in human video synthesis have enabled the generation of high-quality videos through the application of stable diffusion models. However, existing methods predominantly concentrate on animating solely the human element…
Synthesizing photo-realistic images and videos is at the heart of computer graphics and has been the focus of decades of research. Traditionally, synthetic images of a scene are generated using rendering algorithms such as rasterization or…
Existing 4D synthesis methods primarily focus on object-level generation or dynamic scene synthesis with limited novel views, restricting their ability to generate multi-view consistent and immersive dynamic 4D scenes. To address these…
We introduce X-Ray, a novel 3D sequential representation inspired by the penetrability of x-ray scans. X-Ray transforms a 3D object into a series of surface frames at different layers, making it suitable for generating 3D models from…
Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to…
We present GuidedSceneGen, a text-to-3D generation framework that produces metrically accurate, globally consistent, and semantically interpretable indoor scenes. Unlike prior text-driven methods that often suffer from geometric drift or…
Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying…
Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a…
3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid…
Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation pipelines rely heavily on human…
Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the…
Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background…