Sonyさんが再投稿しました
🎉We are pleased to share that 18 research papers from Sony* have been accepted at the IEEE / CVF Computer Vision and Pattern Recognition Conference (#CVPR2026), to be held in Colorado, US, June 3–7. Please join us for our presentations! * Papers authored or co-authored by Sony researchers. 📖Accepted Papers 🔹 PAVAS: Physics-Aware Video-to-Audio Synthesis 🔗 https://lnkd.in/g-ms8ncj 🔹 B³-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates 🔗 https://lnkd.in/ge5iQwsb 🔹 Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision 🔗 https://lnkd.in/gn8RGzhz 🔹 Dark3R: Learning Structure from Motion in the Dark 🔗 https://lnkd.in/gJcCvx2J 🔹 EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer 🔗 https://lnkd.in/gD6pFk-p 🔹 Learning Compact 3D Representations from Feed-Forward Novel View Synthesis 🔗 https://lnkd.in/gVT-yGDR 🔹 MeanFlow Transformers with Representation Autoencoders 🔗 https://lnkd.in/gSZRdQja 🔹 PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation 🔗 https://lnkd.in/gKsg9Z-X 🔹 RewardFlow: Generate Images by Optimizing What You Reward 🔗 https://lnkd.in/gC7CTB9m 🔹 UniCompress: Token Compression for Unified Vision–Language Understanding and Generation 🔗 https://lnkd.in/gqpKNDpf 🔹 VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations 🔗 https://lnkd.in/g8D36-N9 🔹 Asynchronous Temporal Modeling with Two-Agent Framework for Streaming Dense Video Captioning 🔗 https://lnkd.in/gyhSZan7 🔹 BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models 🔗 https://lnkd.in/gzxtVQ8m 🔹 Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models 🔗 https://lnkd.in/gY4D2uzh 🔹 Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal 🔗 https://lnkd.in/g9wDgqEn 🔹 Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation 🔗 https://lnkd.in/ghNC5B3p 🔹 Face Time Traveller: Travel Through Ages Without Losing Identity 🔗 https://lnkd.in/getCXahN 🔹 UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models 🔗 https://lnkd.in/geHus5rd SonyAI #CVPR2026 #ComputerVision #AI #Research #Innovation #PatternRecognition #Sony #Research