Related papers: 3D4D: An Interactive, Editable, 4D World Model via…
The blooming of virtual reality and augmented reality (VR/AR) technologies has driven an increasing demand for the creation of high-quality, immersive, and dynamic environments. However, existing generative techniques either focus solely on…
Understanding 3D scenes in open-world settings poses fundamental challenges for vision and robotics, particularly due to the limitations of closed-vocabulary supervision and static annotations. To address this, we propose a unified…
World models have made significant progress in modeling dynamic environments; however, most embodied world models are still restricted to 2D representations, lacking the comprehensive multi-view information essential for embodied spatial…
We present Stable Video 4D 2.0 (SV4D 2.0), a multi-view video diffusion model for dynamic 3D asset generation. Compared to its predecessor SV4D, SV4D 2.0 is more robust to occlusions and large motion, generalizes better to real-world…
Modeling dynamic 3D scenes is challenging due to their high-dimensional nature, which requires aggregating information from multiple views to reconstruct time-evolving 3D geometry and motion. We present a novel multi-video 4D Gaussian…
Learning 4D language fields to enable time-sensitive, open-ended language queries in dynamic scenes is essential for many real-world applications. While LangSplat successfully grounds CLIP features into 3D Gaussian representations,…
Creating high-quality and interactive virtual environments, such as games and simulators, often involves complex and costly manual modeling processes. In this paper, we present Video2Game, a novel approach that automatically converts videos…
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…
We consider the problem of novel-view synthesis (NVS) for dynamic scenes. Recent neural approaches have accomplished exceptional NVS results for static 3D scenes, but extensions to 4D time-varying scenes remain non-trivial. Prior efforts…
Envisioning physically plausible outcomes from a single image requires a deep understanding of the world's dynamics. To address this, we introduce PhysGen3D, a novel framework that transforms a single image into an amodal, camera-centric,…
Instruction-guided generative models, especially those using text-to-image (T2I) and text-to-video (T2V) diffusion frameworks, have advanced the field of content editing in recent years. To extend these capabilities to 4D scene, we…
Existing dynamic scene generation methods mostly rely on distilling knowledge from pre-trained 3D generative models, which are typically fine-tuned on synthetic object datasets. As a result, the generated scenes are often object-centric and…
Recent advances in 4D generation mainly focus on generating 4D content by distilling pre-trained text or single-view image-conditioned models. It is inconvenient for them to take advantage of various off-the-shelf 3D assets with multi-view…
We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric…
We propose a novel-view augmentation (NOVA) strategy to train NeRFs for photo-realistic 3D composition of dynamic objects in a static scene. Compared to prior work, our framework significantly reduces blending artifacts when inserting…
Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native video-to-4D shape generation framework that synthesizes a single…
Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical constraints of traditional simulators. However, they…
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…
Recent 3D world modeling systems based on generative scene synthesis, such as Marble, can create coherent and explorable 3D environments, yet their outputs are typically static monolithic assets with limited editability and physical…
World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely image-based forecasting or reasoning over partial 3D geometry, limiting their ability to…