Related papers: Any4D: Unified Feed-Forward Metric 4D Reconstructi…
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…
Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is confined to their training domains. These methods fail to…
Joint estimation of surface normals and depth is essential for holistic 3D scene understanding, yet high-resolution prediction remains difficult due to the trade-off between preserving fine local detail and maintaining global consistency.…
While the keypoint-based maps created by sparse monocular simultaneous localisation and mapping (SLAM) systems are useful for camera tracking, dense 3D reconstructions may be desired for many robotic tasks. Solutions involving depth cameras…
Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but they fundamentally suffer from a Memory Demand Dilemma: The…
Reconstructing 4D dynamic scenes from casually captured monocular videos is valuable but highly challenging, as each timestamp is observed from a single viewpoint. We introduce Vivid4D, a novel approach that enhances 4D monocular video…
Reliable 4D object detection, which refers to 3D object detection in streaming video, is crucial for perceiving and understanding the real world. Existing open-set 4D object detection methods typically make predictions on a frame-by-frame…
We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing point tracking methods, our approach delivers…
Recent advances in 2D/3D generative models enable the generation of dynamic 3D objects from a single-view video. Existing approaches utilize score distillation sampling to form the dynamic scene as dynamic NeRF or dense 3D Gaussians.…
There has been great progress in improving numerical weather prediction and climate models using machine learning. However, most global models act at a kilometer-scale, making it challenging to model individual clouds and factors such as…
We present a novel framework for generating high-quality, animatable 4D avatar from a single image. While recent advances have shown promising results in 4D avatar creation, existing methods either require extensive multiview data or…
Methods for 3D reconstruction from posed frames require prior knowledge about the scene metric range, usually to recover matching cues along the epipolar lines and narrow the search range. However, such prior might not be directly available…
Real-time 3D reconstruction enables fast dense mapping of the environment which benefits numerous applications, such as navigation or live evaluation of an emergency. In contrast to most real-time capable approaches, our approach does not…
Recent advances in 4D content generation have attracted increasing attention, yet creating high-quality animated 3D models remains challenging due to the complexity of modeling spatio-temporal distributions and the scarcity of 4D training…
We address the problem of recovering a time-varying 4D distribution from a sparse sequence of 2D projections - analogous to novel-view synthesis from sparse cameras, but applied to the 4D transverse phase space density $\rho(x,p_x,y,p_y)$…
Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is particularly challenging in dynamic…
Given the high complexity of directly generating high-dimensional data such as 4D, we present 4DVD, a cascaded video diffusion model that generates 4D content in a decoupled manner. Unlike previous multi-view video methods that directly…
Feedforward reconstruction is crucial for autonomous driving applications, where rapid scene reconstruction enables efficient utilization of large-scale driving datasets in closed-loop simulation and other downstream tasks, eliminating the…
Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditional methods achieve high fidelity,…
Multi-person identity-preserving generation requires binding multiple reference faces to specified locations under a text prompt. Strong identity/layout conditions often trigger copy-paste shortcuts and weaken prompt-driven controllability.…