SIGGRAPH 2021 학회에서 주목도 높았던 연구 세션 및 키워드들 정리



TOG: Vol 40, No 4

SIG21에서 주목도 높은 연구 세션들 (순서 의미없음):

  1. Neural solver for blah blah
  2. Video, portrait, image editing (sometimes with GANs)
  3. Neural, real-time, differentiable rendering
  4. Rendering theory
  5. Denoising and guiding
  6. Human, face, character animation and control (learning)
  7. Surfaces, curves, ribbons, and wires
  8. Appearance
  9. Deformation
  10. Fabrication
  11. Computational photography

SIG21에서 주목도 높은 키워드들 (순서 의미없음):

  1. Physical simulation
  2. Neural networks
  3. Ray tracing
  4. Shape modeling
  5. Animation
  6. Mesh geometry models 

댓글

댓글 쓰기

이 블로그의 인기 게시물

기록: UCL Course on RL 요약 및 정리 (Lecture 9: Exploration and Exploitation)

이미지
This post covers not only  Lecture 9: Exploration and Exploitation (davidsilver.uk)  but also : 'Reinforcement Learning' 카테고리의 글 목록 (yjjo) The Multi-Armed Bandit Problem and Its Solutions (lilianweng.github.io) Bayesian Bandits - Thompson Sampling (tistory.com) The entire course materials can be found on the following page:  Teaching - David Silver . Lecture Goal MDP를 풀 때 exploration과 exploitation 중 어느 한 쪽만 사용하면 optimality에 도달하지 못한다 (trade-off). 본 강의에서는 둘 사이의 균형을 맞추는 알고리즘을 소개한다. Credit: UC Berkeley Intro to AI course lecture 11 Takeaway Use (Bayes-) UCB algorithms Exploration vs. Exploitation Dilemma Exploitation: make the best decision given current information E.g., go to your favorite restaurant Exploration: gather more information E.g., try a new restaurant Dilemma The best long-term strategy may involve short-term sacrifices and risks How does an agent obtain enough information to make the best overall decisions with the lowest sacrifices? [In-A-Nutshell] Key Princip...
자세한 내용 보기

기록: UCL Course on RL 요약 및 정리 (Lecture 8: Integrating Learning and Planning)

이미지
This post covers  Lecture 8: Integrating Learning and Planning (davidsilver.uk) : The entire course materials can be found on the following page:  Teaching - David Silver . Lecture Goal Opening remarks: 지금껏 known MDP의 경우, model을 알고 있으므로 dynamic programming등 planning 기법을 이용하여 최적의 value function이나 policy를 구할 수 있었다 (이를 MDP를 푼다 고 표현한다).  지금껏 unknown MDP의 경우, environment와의 상호작용(experience)을 통해 최적의 value/policy를 학습하였다 ( learning ).  Unknown MDP 를 풀 때도 experience를 통해, policy나 value만 학습하는 게 아니라,  model (i.e., expected rewards and transition probability) 자체를 학습 한다면 planning 기법을 사용하여 좀 더 효율적으로 MDP를 풀 수 있지 않을까?  본 강의에서는 unknown MDP를 풀기 위해 learning과 planning을 통합적으로 이용하는 model-based reinforcement learning 방법을 배운다. Learning, simulation & planning, Dyna-Q, Monte-Carlo tree search Credit:  Field Report: Applying Monte Carlo Tree Search for Program Synthesis Model Given an MDP \((S,A,T,R)\), a model \(M=(T,R)\) represents state transitions and expected rewards: \(...
자세한 내용 보기

기록: UCL Course on RL 요약 및 정리 (Lecture 5: Model-Free Control)

이미지
This post covers  Lecture 5: Model-Free Control (davidsilver.uk) The entire course materials can be found on the following page:  Teaching - David Silver . Lecture Goal Solve an unknown MDP All information of an MDP is not necessarily given (e.g., reward, transition probabilities, etc.) Model-free prediction: estimate the value function of an unknown MDP ( lecture 4 ) Model-free control: optimize the value function of an unknown MDP (this lecture) On-policy and off-policy learning GLIE Monte-Carlo control , SARSA , Q-learning On-Policy Learning vs. Off-Policy Learning On-policy "Learn on the job" Learn about (how to reach) the optimal policy from experience sampled from the entire policy space from scratch Off-policy "Look over someone's (or oneself's) shoulder" Learn about (how to reach) the optimal policy from experience sampled from the given exemplar policy (i.e.,  behaviors ) exemplar policy = guidance, teacher, advisor (optimal policy에 비해 꼭 낫다는 의미는...
자세한 내용 보기