pfung (@philfung)

2025-05-16 | โค๏ธ 2 | ๐Ÿ” 0


cool approach: This Berkeley paper ditched simulator physics completely. The simulator is only for โ€œrenderingโ€. (i.e. gen more realistic video data based on splats and inv. kinematics only) https://x.com/philfung/status/1923485144125759770/photo/1

๐Ÿ”— ์›๋ณธ ๋งํฌ

๋ฏธ๋””์–ด

image


Auto-generated - needs manual review

์ธ์šฉ ํŠธ์œ—

Max Fu (@letian_fu)

Tired of teleoperating your robots? We built a way to scale robot datasets without teleop, dynamic simulation, or even robot hardware. Just one smartphone scan + one human hand demo video โ†’ thousands of diverse robot trajectories. Trainable by diffusion policy and VLA models as-is. Introducing: Real2Render2Real ๐Ÿ‘‰ https://t.co/lRHspvFpwy

์›๋ณธ ํŠธ์œ—

๐ŸŽฌ ์˜์ƒ

Tags

domain-vision-3d domain-rendering domain-simulation