3 papers
cs.CV2026
When Depth Hurts: Reliability-Aware Geometry Distillation for Depth-Free RGB-D Salient Object Detection
Xuehao Wang, Jiaxin Hua, Runmei Li +4
Depth can resolve appearance ambiguity in RGB-D salient object detection (SOD), yet sensor depth is not uniformly reliable. Missing regions, blurred boundaries, and structural arti…
cs.MM2026
EditEmoTalk: Controllable Speech-Driven 3D Facial Animation with Continuous Expression Editing
Diqiong Jiang, Kai Zhu, Dan Song +3
Speech-driven 3D facial animation aims to generate realistic and expressive facial motions directly from audio. While recent methods achieve high-quality lip synchronization, they…
cs.CV2026
GenCAMO: Scene-Graph Contextual Decoupling for Environment-aware and Mask-free Camouflage Image-Dense Annotation Generation
Chenglizhao Chen, Shaojiang Yuan, Xiaoxue Lu +5
Conceal dense prediction (CDP), especially RGB-D camouflage object detection and open-vocabulary camouflage object segmentation, plays a crucial role in advancing the understanding…