TOM-GS uses temporal opacity modulation to make static 3D Gaussians editable video
kwangmoo_yi · x · 2026-07-29
TOM-GS introduces an editable video representation built on static 3D Gaussians with temporal opacity modulation instead of complex spatial deformations.
Key idea:
- Each Gaussian gets a learnable temporal mean and scale that control when it fades in or out.
- The method keeps the 3D geometry static, which makes the representation easier to edit with manual or physics-based tools.
- The paper claims better visual fidelity than prior editable video representations while staying compatible with standard 3D editing workflows.
Related event: TOM-GS Enables Editable Video via Temporal Opacity Modulation(2 posts)→
More from Research
- MIT's Neil Thompson: AI comes for tasks before jobs, and fixed costs favor big firms — bigdata · 2026-10-16
- UMD's PAIR framework bridges perception and action in VLA models via bridge tokens — Kaixi Feng · 2026-10-16
- CI-MSE offline metric hits -0.87 Spearman correlation with real robot task success vs weak raw MSE — chris_j_paxton · 2026-10-16
- Colossal Biosciences uses AI to decode genetic switches behind the extinct dodo — castrotech · 2026-10-16
- Colossal Biosciences uses AI to identify gene switches in dodo de-extinction push — castrotech · 2026-10-16
- Cheng Lou open-sources Handwired: hand-written weights turn code into training-free neural nets — dotey · 2026-10-16