Related papers: Not All Frames Are Equal: Complexity-Aware Masked …
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment…
LiDAR and camera are two modalities available for 3D semantic segmentation in autonomous driving. The popular LiDAR-only methods severely suffer from inferior segmentation on small and distant objects due to insufficient laser points, while…
The recent Segment Anything Model 2 (SAM2) has demonstrated exceptional capabilities in interactive object segmentation for both images and videos. However, as a foundational model on interactive segmentation, SAM2 performs segmentation…
Because diffusion models have shown impressive performances in a number of tasks, such as image synthesis, there is a trend in recent works to prove (with certain assumptions) that these models have strong approximation capabilities. In…
We propose a manifold matching approach to generative models which includes a distribution generator (or data generator) and a metric generator. In our framework, we view the real data set as some manifold embedded in a high-dimensional…
Real-time motion generation -- which is essential for achieving reactive and adaptive behavior -- under kinodynamic constraints for high-dimensional systems is a crucial yet challenging problem. We address this with a two-step approach:…
Masked Diffusion Models (MDMs) offer flexible, non-autoregressive generation, but this freedom introduces a challenge: final output quality is highly sensitive to the decoding order. We are the first to formalize this issue, attributing the…
Masked diffusion models (MDM) are powerful generative models for discrete data that generate samples by progressively unmasking tokens in a sequence. Each token can take one of two states: masked or unmasked. We observe that token sequences…
Generating 3D human motions from text is a challenging yet valuable task. The key aspects of this task are ensuring text-motion consistency and achieving generation diversity. Although recent advancements have enabled the generation of…
Synthesizing realistic and spatially precise anomalies is essential for enhancing the robustness of industrial anomaly detection systems. While recent diffusion-based methods have demonstrated strong capabilities in modeling complex defect…
Sensor-based human activity recognition is important in daily scenarios such as smart healthcare and homes due to its non-intrusive privacy and low cost advantages, but the problem of out-of-domain generalization caused by differences in…
Observable motion in videos can give rise to the definition of objects moving with respect to the scene. The task of segmenting such moving objects is referred to as motion segmentation and is usually tackled either by aggregating motion…
Co-Speech Gesture Video Generation aims to generate vivid speech videos from audio-driven still images, which is challenging due to the diversity of body parts in terms of motion amplitude, audio relevance, and detailed features. Relying…
This paper introduces a fast algorithm for randomized computation of a low-rank Dynamic Mode Decomposition (DMD) of a matrix. Here we consider this matrix to represent the development of a spatial grid through time e.g. data from a static…
Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…
In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action recognition in particular. Thus far, the vision community…
In this paper, we present a feature-aware SPH method for the concurrent and automated isotropic unstructured mesh generation. Two additional objectives are achieved with the proposed method compared to the original SPH-based mesh generator…
We present a data-efficient, multiscale framework for predicting the density profiles of confined fluids at the nanoscale. While accurate density estimates require prohibitively long timescales that are inaccessible by ab initio molecular…
Existing methods of cross-modal domain adaptation for 3D semantic segmentation predict results only via 2D-3D complementarity that is obtained by cross-modal feature matching. However, as lacking supervision in the target domain, the…
Masked diffusion models (MDMs) have achieved notable progress in modeling discrete data, while their potential in molecular generation remains underexplored. In this work, we explore their potential and introduce the surprising result that…