Related papers: Grab-3D: Detecting AI-Generated Videos from 3D Geo…
Predominant techniques on talking head generation largely depend on 2D information, including facial appearances and motions from input face images. Nevertheless, dense 3D facial geometry, such as pixel-wise depth, plays a critical role in…
Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition generation on globally reconstructed 3D scenes by rendering…
When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because, with video, the temporal dimension poses significant…
Current texture synthesis methods, which generate textures from fixed viewpoints, suffer from inconsistencies due to the lack of global context and geometric understanding. Meanwhile, recent advancements in video generation models have…
Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. Additionally, 3D scene generation is vital for advancing embodied AI and world models, which depend…
We investigate a challenging task of dynamic scene geometry estimation, which requires representing both spatial and temporal features. Typically, existing methods align the two features into a unified latent space to model scene geometry.…
Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible errors due to…
Understanding the 3D geometry and semantics of driving scenes is critical for safe autonomous driving. Recent advances in 3D occupancy prediction have improved scene representation but often suffer from visual inconsistencies, leading to…
3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness critically depends on the quality of the initialized point cloud. Specifically, achieving uniform…
Video world models aim to simulate dynamic, real-world environments, yet existing methods struggle to provide unified and precise control over camera and multi-object motion, as videos inherently capture dynamics in the projected 2D image…
The recently developed Sora model [1] has exhibited remarkable capabilities in video generation, sparking intense discussions regarding its ability to simulate real-world phenomena. Despite its growing popularity, there is a lack of…
Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that…
We introduce MEt3R, a metric for multi-view consistency in generated images. Large-scale generative models for multi-view image generation are rapidly advancing the field of 3D inference from sparse observations. However, due to the nature…
Point cloud registration aims at estimating the geometric transformation between two point cloud scans, in which point-wise correspondence estimation is the key to its success. In addition to previous methods that seek correspondences by…
Video generation is an interesting problem in computer vision. It is quite popular for data augmentation, special effect in move, AR/VR and so on. With the advances of deep learning, many deep generative models have been proposed to solve…
Recent works have shown that 3D-aware GANs trained on unstructured single image collections can generate multiview images of novel instances. The key underpinnings to achieve this are a 3D radiance field generator and a volume rendering…
Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated under ideal, degradation-free imaging conditions, whereas…
Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the…
Humans naturally retain memories of permanent elements, while ephemeral moments often slip through the cracks of memory. This selective retention is crucial for robotic perception, localization, and mapping. To endow robots with this…
In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…