activity
20242026
collaborators

5 papers

cs.CV2026

MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation

Ronyu Zhang, Aosong Cheng, Gaole Dai +8

Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error…

cs.CV2026

VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction

Xun Chen, Tianchen Deng, Rui Wang +5

3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subsequent operations like offset…

cs.CV2026

ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics

Sylvia Yuan, Dan Wang, Ravi Ramamoorthi +1

We present ArtMesh, a mesh-native method for reconstructing articulated objects explicitly as connected triangle meshes with per-part rigid motion from multi-view images in start a…

cs.CV2025

ABCDWaveNet: Advancing Robust Road Ponding Detection in Fog through Dynamic Frequency-Spatial Synergy

Ronghui Zhang, Dakang Lyu, Tengfei Li +7

Road ponding presents a significant threat to vehicle safety, particularly in adverse fog conditions, where reliable detection remains a persistent challenge for Advanced Driver As…

cs.CV2024

GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder

Junzhou Chen, Xuan Wen, Ronghui Zhang +4

Unsupervised Domain Adaptation (UDA) aims to adapt a model trained on a labeled source domain to an unlabeled target domain by addressing the domain shift. Existing Unsupervised Do…