π“Ÿ host1.bitchan.one

𓀐 @ErAeN6x4

⏱ 1w seenβ›“ 0πŸ‘ 0β§– 2

filter [-]

languages:onother

>mfw Research news 10/30/2026 >Hierarchical Diffusion for Camera-controlled Autoregressive Video Generation https://kaihua-chen.github.io/wanar_fixar >Self-Consistency Geometry Injection for Multi-view Consistent Image Generation https://arxiv.org/abs/2610.38518 >Aligning Misaligned Benchmarks for Single-View Novel View Synthesis https://arxiv.org/abs/2610.38349 >V-CAPE: Visual Consistency Assessment for Product Image Editing https://arxiv.org/abs/2610.38611 >Detecting Fine-Grained Differences…⏱ 1w↩
>mfw Research news 10/30/2026 >Hierarchical Diffusion for Camera-controlled Autoregressive Video Generation https://kaihua-chen.github.io/wanar_fixar >Self-Consistency Geometry Injection for Multi-view Consistent Image Generation https://arxiv.org/abs/2610.38518 >Aligning Misaligned Benchmarks for Single-View Novel View Synthesis https://arxiv.org/abs/2610.38349 >V-CAPE: Visual Consistency Assessment for Product Image Editing https://arxiv.org/abs/2610.38611 >Detecting Fine-Grained Differences between Image Datasets https://arxiv.org/abs/2610.38547 >Evaluating Visual Realism of AI-Generated Videos with Eye Tracking https://arxiv.org/abs/2610.38825 >Automatic Iconographic Annotation of Medieval Illuminations: Comparing Generative Vision-Language Models and Supervised Discriminative Classifiers https://arxiv.org/abs/2610.38462 >Residual Motion Splatting for Continuous Space-Time Video Super-Resolution https://arxiv.org/abs/2610.38499 >ConvRoute-ViT: Convolutional Token Routing for Efficient Vision Transformers https://arxiv.org/abs/2610.38284 >Intersectional Invariant Learning for Fair Deepfake Detection https://arxiv.org/abs/2610.37881 >WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video https://arxiv.org/abs/2610.38352 >MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching https://arxiv.org/abs/2610.02260⏱ 1w↩