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
- CIMC and Apart Research launch a San Francisco sprint on AI sentience and alignment — matiroy · 2026-07-29
- A RL lecture revisits how KL regularization changes as methods evolve — cwolferesearch · 2026-07-29
- OpenAI Foundation is urged to fund AI research hubs in the Global South — ShakeelHashim · 2026-07-29
- Sarah Guo says AI still needs more tinkering in the physical world — saranormous · 2026-07-29
- Annals of Mathematics paper proves a 1853 design conjecture — MarioKrenn6240 · 2026-07-29
- Audit finds up to 12% of GPQA, MMLU-Pro, and MMMU-Pro questions were broken — pawofdoom · 2026-07-29