MLP-Splatting at ECCV 2026: one small MLP per object replaces thousands of Gaussians
AjdDavison · x · 2026-09-08
The MLP-Splatting paper will be presented at ECCV 2026 (Poster #277, Thu 10:30) and at the NeuSLAM workshop (Sep 8, 14:00). Instead of thousands of Gaussian primitives, it assigns one small MLP per object/part and makes hundreds of tiny MLPs "splattable", enabling compact 3D scenes with fewer primitives; object-level structure emerges from RGB alone. Authors include Xin Kong and Andrew Davison.
More from Research
- Mathematician argues papers should shift from proving conjectures to sharing insight — tak3sh8 · 2026-09-08
- Niantic's AutoCompass trains accurate visual localization from noisy GPS labels — ducha_aiki · 2026-09-08
- Apex unveils Astra, an automated AI research system aimed at AI improving AI — thetripathi58 · 2026-09-08
- More Ukrainian teams join CV research map with USDZ-prediction approach to object alignment and animation — ducha_aiki · 2026-09-08
- JustRL II adds token-level critic to GRPO for 128k long-CoT RL, lifting 2B model AIME25 from 61 to 81 — zibuyu9 · 2026-09-08
- Helsinki's Luigi Acerbi recruiting PhD/postdoc on amortized probabilistic ML for decision-making — LucaAmb · 2026-09-08