Related papers: SPRig: Self-Supervised Pose-Invariant Rigging from…

Capturing both geometry and rigid motion for structured dynamic objects, like multi-part assemblies or jointed mechanisms, remains a key challenge. Existing dynamic methods, such as deformable meshes or 3DGS, rely on unstructured…

We present MoRig, a method that automatically rigs character meshes driven by single-view point cloud streams capturing the motion of performing characters. Our method is also able to animate the 3D meshes according to the captured point…

This paper considers the problem of modeling articulated objects captured in 2D videos to enable novel view synthesis, while also being easily editable, drivable, and re-posable. To tackle this challenging problem, we propose RigGS, a new…

As a basic component of SE(3)-equivariant deep feature learning, steerable convolution has recently demonstrated its advantages for 3D semantic analysis. The advantages are, however, brought by expensive computations on dense, volumetric…

Rotation averaging is a synchronization process on single or multiple rotation groups, and is a fundamental problem in many computer vision tasks such as multi-view structure from motion (SfM). Specifically, rotation averaging involves the…

Iterative methods are widely used for solving partial differential equations (PDEs). However, the difficulty in eliminating global low-frequency errors significantly limits their convergence speed. In recent years, neural networks have…

Unsupervised skill discovery in reinforcement learning (RL) aims to learn diverse behaviors without relying on external rewards. However, current methods often overlook the periodic nature of learned skills, focusing instead on increasing…

Although deep learning (DL) has gained much popularity for accelerated magnetic resonance imaging (MRI), recent studies have shown that DL-based MRI reconstruction models could be oversensitive to tiny input perturbations (that are called…

Spiking neural networks have gained significant attention due to their brain-like information processing capabilities. The use of surrogate gradients has made it possible to train spiking neural networks with backpropagation, leading to…

Video semantic segmentation has achieved great progress under the supervision of large amounts of labelled training data. However, domain adaptive video segmentation, which can mitigate data labelling constraints by adapting from a labelled…

Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the…

Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging, yet reconstructing high-resolution 3D data remains computationally demanding. Non-Cartesian reconstructions require repeated non-uniform FFTs, and the commonly used…

Symbolic Regression (SR) aims to discover interpretable equations from observational data, with the potential to reveal underlying principles behind natural phenomena. However, existing approaches often fall into the Pseudo-Equation Trap:…

Masked Image Modeling (MIM) techniques have redefined the landscape of computer vision, enabling pre-trained models to achieve exceptional performance across a broad spectrum of tasks. Despite their success, the full potential of MIM-based…

Discontinuous Galerkin (DG) methods for hyperbolic partial differential equations (PDEs) with explicit time-stepping schemes, such as strong stability-preserving Runge-Kutta (SSP-RK), suffer from time-step restrictions that are…

We propose a novel method for large-scale image stitching that is robust against repetitive patterns and featureless regions in the imagery. In such cases, state-of-the-art image stitching methods easily produce image alignment artifacts,…

Standard representation probing for visual models relies on mathematically permutation-invariant operations like Global Average Pooling (GAP) or CLS tokens, treating patch representations as an unstructured bag-of-words. We challenge this…

Humanoid robot manipulation is a crucial research area for executing diverse human-level tasks, involving high-level semantic reasoning and low-level action generation. However, precise scene understanding and sample-efficient learning from…

Despite advancements in Neural Implicit models for 3D surface reconstruction, handling dynamic environments with interactions between arbitrary rigid, non-rigid, or deformable entities remains challenging. The generic reconstruction methods…

The dressing method is a technique to construct new solutions in non-linear sigma models under the provision of a seed solution. This is analogous to the use of autoBacklund transformations for systems of the sine-Gordon type. In a recent…