RT @_crockwell: Excited to share ☀️Lightspeed⚡, a photorealistic, synthetic dataset with ground truth pose used for benchmarking alongside….

RT @_crockwell: Ever wish YouTube had 3D labels?. 🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with….

RT @jin_linyi: Introducing 👀Stereo4D👀. A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *….

RT @ambie_kk: Introducing Doppelgangers++! 🚀 An enhanced pairwise image classifier that tackles visual aliasing (doppelgangers) to improve….

RT @ducha_aiki: Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features . Yuanbo Xiangli, Ruojin Cai, Hanyu Chen, Jeffre….

RT @gene_ch0u: We've released our paper "Generating 3D-Consistent Videos from Unposed Internet Photos"! Video models like Luma generate pre….

RT @Haian_Jin: Check out our recent work “Neural Gaffer: Relighting Any Object via Diffusion” 📷🌈, an end-to-end 2D relighting diffusion mod….

RT @gene_ch0u: Introducing MegaScenes—a scene-level dataset containing 100K SfM reconstructions and 2M images with open content licenses. W….