Diffusion-based Generation, Optimization, and Planning in 3D Scenes (CVPR 2023)

An Embodied Generalist Agent in 3D World

GenMM_SIGGRAPH2023

How LLMs Are Used in Recommendation Systems

HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes (NeurIPS 2022)

NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields

PolyFly: Polytopic Planning for Collision-Free Aerial Transportation

Модель распространения движения робота: генерация движения для роботизированных персонажей.

Почему диффузия работает лучше, чем авторегрессия?

MonoPerfCap: Human Performance Capture from Monocular Video - ACM TOG (presented SIGGRAPH 2018)

ViPlanner: Visual Semantic Imperative Learning for Local Navigation (ICRA 2024)

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

Capturing Detailed Deformations of Moving Human Bodies | Siggraph 2021

Yi Ma: Learning to Detect Geometric Structures from Images for 3D Parsing

[CVPR 2023] DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients

Actor-Critic Model Predictive Control (ICRA 2024)

$1 vs $1,000,000,000 Футуристических Технологий!

ECON: Explicit Clothed humans Obtained from Normals (CVPR 2023)

25 Запрещенных Гаджетов, Которые Вы Можете Купить Онлайн

PARTICULAS CON FONDO NEGRO 🌈 FONDO ANIMADO - VFX - GRATIS ✅ (no copyright)💪

DiffRF: Rendering-guided 3D Radiance Field Diffusion (CVPR'2023)