5 papers
Relighting as a Probe of Visual Priors via Augmented Latent Intrinsics
Xiaoyan Xing, Xiao Zhang, Sezer Karaoglu +2
Image-to-image relighting requires representations that separate illumination from scene properties while preserving dense geometry, material, and photometric cues. We use this tas…
ViT-5: Vision Transformers for The Mid-2020s
Feng Wang, Sucheng Ren, Tiezheng Zhang +4
This work presents a systematic investigation into modernizing Vision Transformer backbones by leveraging architectural advancements from the past five years. While preserving the…
Name That Part: 3D Part Segmentation and Naming
Soumava Paul, Prakhar Kaushik, Ankit Vaidya +2
We address semantic 3D part segmentation: decomposing objects into parts with meaningful names. While datasets exist with part annotations, their definitions are inconsistent acros…
Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
Varun Varma Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan +1
Video generators are increasingly evaluated as potential world models, which requires them to encode and understand physical laws. We investigate their representation of a fundamen…
Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning
Tianchong Jiang, Jingtian Ji, Xiangshan Tan +4
We study view-invariant imitation learning by explicitly conditioning policies on camera extrinsics. Using Plucker embeddings of per-pixel rays, we show that conditioning on extrin…