6 papers
MechVerse: Evaluating Physical Motion Consistency in Video Generation Models
Rahul Jain, Mayank Patel, Asim Unmesh +1
Text- and image-conditioned video generation models have achieved strong visual fidelity and temporal coherence, but they often fail to generate motion governed by kinematic and ge…
Exploring Vision-Language Models for Open-Vocabulary Zero-Shot Action Segmentation
Asim Unmesh, Kaki Ramesh, Mayank Patel +2
Temporal Action Segmentation (TAS) requires dividing videos into action segments, yet the vast space of activities and alternative breakdowns makes collecting comprehensive dataset…
Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
Dong In Lee, Hyungjun Doh, Seunggeun Chi +3
Recent progress in 4D representations, such as Dynamic NeRF and 4D Gaussian Splatting (4DGS), has enabled dynamic 4D scene reconstruction. However, text-driven 4D scene editing rem…
Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction
Hyungjun Doh, Dong In Lee, Seunggeun Chi +4
We introduce a novel framework for reconstructing dynamic human-object interactions from monocular video that overcomes challenges associated with occlusions and temporal inconsist…
CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image
Wonseok Roh, Hwanhee Jung, Jong Wook Kim +6
Recently, generalizable feed-forward methods based on 3D Gaussian Splatting have gained significant attention for their potential to reconstruct 3D scenes using finite resources. T…
Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
Seunggeun Chi, Pin-Hao Huang, Enna Sachdeva +3
We study the problem of estimating the body movements of a camera wearer from egocentric videos. Current methods for ego-body pose estimation rely on temporally dense sensor data,…