Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer
Haoyu Wu, Jingyi Xu, Qiaomu Miao +2
Rotary positional embeddings (RoPE) are widely used in diffusion transformers (DiTs) to encode spatial relationships, yet their behavior with mixed-resolution tokens remains undere…
cs.CV2025
Multi-view Gaze Target Estimation
Qiaomu Miao, Vivek Raju Golani, Jingyi Xu +3
This paper presents a method that utilizes multiple camera views for the gaze target estimation (GTE) task. The approach integrates information from different camera views to impro…