森島研究室 https://validator.w3.org/feed/docs/rss2.html LinSSS: linear decomposition of heterogeneous subsurface scattering for real-time screen-space rendering Audio-Visual Object Removal in 360-Degree Videos Song2Face: Synthesizing Singing Facial Animation from Audio LineChaser: 視覚障碍者が列に並ぶためのスマートフォン型支援システム Visual Computing 2020 WISS 2020: 第28回インタラクティブシステムとソフトウェアに関するワークショップ Asynchronous Eulerian Liquid Simulation Visual Computing 2020 GPU Smoke Simulation with Adaptive DCT Compression Visual Computing 2020 第23回 画像の認識・理解シンポジウム（MIRU2020） 第23回 画像の認識・理解シンポジウム（MIRU2020） LineChaser: A Smartphone-Based Navigation System for Blind People to Stand in Lines コンタクト Song2Face: Synthesizing Singing Facial Animation from Audio Computer Vision – ACCV 2020 Computer Vision – ACCV 2020 SIGGRAPH Asia 2020 Technical Communications SIGGRAPH Asia 2020 Technical Communications Song2Face: Synthesizing Singing Facial Animation from Audio Do We Need Sound for Sound Source Localization? Asian Conference on Computer Vision 2020 (ACCV2020) Asian Conference on Computer Vision 2020 (ACCV2020) CHI Conference on Human Factors in Computing Systems (CHI ’21) Journal of Information Processing Journal of Information Processing 25th International Conference on Pattern Recognition (ICPR2020) 25th International Conference on Pattern Recognition (ICPR2020) SIGGRAPH Asia 2020 SIGGRAPH Asia 2020 MirrorNet: A Deep Reflective Approach to 2D Pose Estimation for Single-Person Images Song2Face: Synthesizing Singing Facial Animation from Audio Do We Need Sound for Sound Source Localization? LineChaser: A Smartphone-Based Navigation System for Blind People to Stand in Lines Object-oriented Representation Learningの実世界データ適用に向けた最新手法の性能分析 Visual Computing 2020 Adversarial Knowledge Distillation for a Compact Generator BlindPilot: A Robotic Local Navigation System that Leads Blind People to a Landmark Object BlindPilot: A Robotic Local Navigation System that Leads Blind People to a Landmark Object Shigeo MORISHIMA 森島 繁生 Adversarial Knowledge Distillation for a Compact Generator CHI Conference on Human Factors in Computing Systems (CHI ’21) MirrorNet: A Deep Reflective Approach to 2D Pose Estimation for Single-Person Images Do We Need Sound for Sound Source Localization? 音と画像を用いた演奏の音に連動した動画生成 Object-aware表現学習の安定化のためのKLダイバージェンスの周期性アニーリング Do We Need Sound for Sound Source Localization? ホーム Style Controllable Facial Animation Synthesis from SInging Audio