Related papers: Beyond the Frame: Generating 360 Panoramic Videos …
The growing demand for Embodied AI and VR applications has highlighted the need for synthesizing high-quality 3D indoor scenes from sparse inputs. However, existing approaches struggle to infer massive amounts of missing geometry in large…
Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is…
There are two prevalent ways to constructing 3D scenes: procedural generation and 2D lifting. Among them, panorama-based 2D lifting has emerged as a promising technique, leveraging powerful 2D generative priors to produce immersive,…
The ultimate goal of video generation is to satisfy a fundamental trilemma: achieving high visual quality, maintaining rigorous physical consistency, and enabling precise controllability. While recent models can maintain this balance in…
Virtual reality has been gaining popularity in recent years caused by the proliferation of affordable consumer-grade devices such as Oculus Rift, HTC Vive, and Samsung VR. Amongst the various VR applications, 360{\deg} video streaming is…
Generative video modeling has emerged as a compelling tool to zero-shot reason about plausible physical interactions for open-world manipulation. Yet, it remains a challenge to translate such human-led motions into the low-level actions…
Virtual reality and augmented reality (XR) bring increasing demand for 3D content. However, creating high-quality 3D content requires tedious work that a human expert must do. In this work, we study the challenging task of lifting a single…
We propose a learning-based approach for novel view synthesis for multi-camera 360$^{\circ}$ panorama capture rigs. Previous work constructs RGBD panoramas from such data, allowing for view synthesis with small amounts of translation, but…
We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video4Spatial, a framework showing that video diffusion models…
We introduce bounded generation as a generalized task to control video generation to synthesize arbitrary camera and subject motion based only on a given start and end frame. Our objective is to fully leverage the inherent generalization…
Text-driven 3D scene generation has seen significant advancements recently. However, most existing methods generate single-view images using generative models and then stitch them together in 3D space. This independent generation for each…
360$^{\circ}$ panoramas are a rich medium, yet notoriously difficult to visualize in the 2D image plane. We explore how intelligent rotations of a spherical image may enable content-aware projection with fewer perceptible distortions.…
Estimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods…
Recent advances in deep learning have significantly improved performance of video prediction. However, state-of-the-art methods still suffer from blurriness and distortions in their future predictions, especially when there are large…
Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images. In this paper, we propose a video generation method based on diffusion models, where the effects of motion are modeled in…
In recent years, the demand for 3D content has grown exponentially with the intelligent upgrade of interactive media, extended reality (XR), and Metaverse industries. In order to overcome the limitations of traditional manual modeling…
While feed-forward 3D reconstruction models have advanced rapidly, they still exhibit degraded performance on panoramas due to spherical distortions. Moreover, existing panoramic 3D datasets are predominantly collected with 360 cameras…
Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated videos still contain visual artifacts arising from 3D…
Video generation models have progressed tremendously through large latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts…
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned…