Related papers: MotionCrafter: Dense Geometry and Motion Reconstru…
Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can…
Reconstructing dynamic 3D scenes from monocular video remains fundamentally challenging due to the need to jointly infer motion, structure, and appearance from limited observations. Existing dynamic scene reconstruction methods based on…
Character image animation has rapidly advanced with the rise of digital humans. However, existing methods rely largely on 2D-rendered pose images for motion guidance, which limits generalization and discards essential 4D information for…
Recent advances in generative models have achieved high-fidelity in 3D human reconstruction, yet their utility for specific tasks (e.g., human 3D segmentation) remains constrained. We propose HumanCrafter, a unified framework that enables…
View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object…
This paper presents DENSER, an efficient and effective approach leveraging 3D Gaussian splatting (3DGS) for the reconstruction of dynamic urban environments. While several methods for photorealistic scene representations, both implicitly…
Recent advancements in personalized Text-to-Video (T2V) generation have made significant strides in synthesizing character-specific content. However, these methods face a critical limitation: the inability to perform fine-grained control…
Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…
Joint 2D cardiac segmentation and 3D volume reconstruction are fundamental to building statistical cardiac anatomy models and understanding functional mechanisms from motion patterns. However, due to the low through-plane resolution of cine…
City scene generation has gained significant attention in autonomous driving, smart city development, and traffic simulation. It helps enhance infrastructure planning and monitoring solutions. Existing methods have employed a two-stage…
We introduce PartCrafter, the first structured 3D generative model that jointly synthesizes multiple semantically meaningful and geometrically distinct 3D meshes from a single RGB image. Unlike existing methods that either produce…
Recent generative models can create visually plausible 3D representations of objects. However, the generation process often allows for implicit control signals, such as contextual descriptions, and rarely supports bold geometric distortions…
Reconstructing 3D objects from a single image is an intriguing but challenging problem. One promising solution is to utilize multi-view (MV) 3D reconstruction to fuse generated MV images into consistent 3D objects. However, the generated…
Recent advancements in 2D/3D generative techniques have facilitated the generation of dynamic 3D objects from monocular videos. Previous methods mainly rely on the implicit neural radiance fields (NeRF) or explicit Gaussian Splatting as the…
Recovering 4D from monocular video, which jointly estimates dynamic geometry and camera poses, is an inevitably challenging problem. While recent pointmap-based 3D reconstruction methods (e.g., DUSt3R) have made great progress in…
Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to…
Controllable 3D scene generation has extensive applications in virtual reality and interior design, where the generated scenes should exhibit high levels of realism and controllability in terms of geometry. Scene graphs provide a suitable…
Vision transformers have recently emerged as an effective alternative to convolutional networks for action recognition. However, vision transformers still struggle with geometric variations prevalent in video data. This paper proposes a…
We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn…
Reconstructing dense, volumetric models of real-world 3D scenes is important for many tasks, but capturing large scenes can take significant time, and the risk of transient changes to the scene goes up as the capture time increases. These…