相关论文: GenDeF: Learning Generative Deformation Field for …

Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly…

We cast multiview reconstruction from unknown pose as a generative modeling problem. From a collection of unannotated 2D images of a scene, our approach simultaneously learns both a network to predict camera pose from 2D image input, as…

We introduce a new generative approach for synthesizing 3D geometry and images from single-view collections. Most existing approaches predict volumetric density to render multi-view consistent images. By employing volumetric rendering using…

We propose an approach to generate images of people given a desired appearance and pose. Disentangled representations of pose and appearance are necessary to handle the compound variability in the resulting generated images. Hence, we…

Recent advances in deep generative models led to the development of neural face video compression codecs that use an order of magnitude less bandwidth than engineered codecs. These neural codecs reconstruct the current frame by warping a…

We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video…

Recovering 3D scenes from sparse views is a challenging task due to its inherent ill-posed problem. Conventional methods have developed specialized solutions (e.g., geometry regularization or feed-forward deterministic model) to mitigate…

We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene. Our work builds upon recent advances in neural implicit representation and uses continuous and…

View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image according to the condition. However, the source contents are…

Graph generative models are essential across diverse scientific domains by capturing complex distributions over relational data. Among them, graph diffusion models achieve superior performance but face inefficient sampling and limited…

Representing and synthesizing novel views in real-world dynamic scenes from casual monocular videos is a long-standing problem. Existing solutions typically approach dynamic scenes by applying geometry techniques or utilizing temporal…

Compositional video generation aims to synthesize multiple instances with diverse appearance and motion. However, current approaches mainly focus on binding semantics, neglecting to understand diverse motion categories specified in prompts.…

The advance of Generative Adversarial Networks (GANs) enables realistic face image synthesis. However, synthesizing face images that preserve facial identity as well as have high diversity within each identity remains challenging. To…

The emerging Neural Radiance Field (NeRF) shows great potential in representing 3D scenes, which can render photo-realistic images from novel view with only sparse views given. However, utilizing NeRF to reconstruct real-world scenes…

We present a method for automatically modifying a NeRF representation based on a single observation of a non-rigid transformed version of the original scene. Our method defines the transformation as a 3D flow, specifically as a weighted…

Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions. In this…

Recent advances in the diffusion models have significantly improved text-to-image generation. However, generating videos from text is a more challenging task than generating images from text, due to the much larger dataset and higher…

We present LARNet, a novel end-to-end approach for generating human action videos. A joint generative modeling of appearance and dynamics to synthesize a video is very challenging and therefore recent works in video synthesis have proposed…

In this paper, we propose a generative model, Temporal Generative Adversarial Nets (TGAN), which can learn a semantic representation of unlabeled videos, and is capable of generating videos. Unlike existing Generative Adversarial Nets…

We suggest a rasterization pipeline tailored towards the need of head-mounted displays (HMD), where latency and field-of-view requirements pose new challenges beyond those of traditional desktop displays. Instead of rendering and warping…