Related papers: AnchorWeave: World-Consistent Video Generation wit…
Maintaining consistent characters, props, and environments across multiple shots is a central challenge in narrative video generation. Existing models can produce high-quality short clips but often fail to preserve entity identity and…
We present I2V3D, a novel framework for animating static images into dynamic videos with precise 3D control, leveraging the strengths of both 3D geometry guidance and advanced generative models. Our approach combines the precision of a…
3D Gaussian Splatting (3DGS) delivers high-fidelity real-time rendering but suffers from geometric and photometric degradations under sparse-view constraints. Current generative restoration approaches are often limited by insufficient…
Simple as it seems, moving an object to another location within an image is, in fact, a challenging image-editing task that requires re-harmonizing the lighting, adjusting the pose based on perspective, accurately filling occluded regions,…
Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges,…
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video.…
This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…
Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned…
Long-horizon video generation suffers from two intertwined issues. First, there is drift, where video quality degrades over time. Second, there are continuity issues which manifest as object permanence issues, or improperly rendering…
In this paper, we explore the overlooked challenge of stability and temporal consistency in interactive video generation, which synthesizes dynamic and controllable video worlds through interactive behaviors such as camera movements and…
We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within…
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…
Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow,…
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view…
Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a…
Generating explorable 3D scenes from a single image is a highly challenging problem in 3D vision. Existing methods struggle to support free exploration, often producing severe geometric distortions and noisy artifacts when the viewpoint…
Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency. This progress inspires us to investigate the potential of these models to ensure dynamic…
Video generation models have become increasingly popular in the last few years, however the standard 2D architectures used today lack natural spatio-temporal modelling capabilities. In this paper, we present a network architecture for video…
Single-image 3D scene reconstruction presents significant challenges due to its inherently ill-posed nature and limited input constraints. Recent advances have explored two promising directions: multiview generative models that train on 3D…
Precise camera control for reshooting dynamic videos is bottlenecked by the severe scarcity of paired multi-view data for non-rigid scenes. We overcome this limitation with a highly scalable self-supervised framework capable of leveraging…