[논문] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
·
Paper Review
https://www.matthewtancik.com/nerf NeRF: Neural Radiance FieldsA method for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views.www.matthewtancik.com AbstractWe present a method that achieves SOTA results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene ..
[논문] 3D Gaussian Splatting for Real-Time Radiance Field Rendering
·
Paper Review
3D Gaussian Splatting for Real-Time Radiance Field Rendering[Müller 2022] Müller, T., Evans, A., Schied, C. and Keller, A., 2022. Instant neural graphics primitives with a multiresolution hash encoding [Hedman 2018] Hedman, P., Philip, J., Price, T., Frahm, J.M., Drettakis, G. and Brostow, G., 2018. Deep blendingrepo-sam.inria.frAbstractRadiance Field method : 여러 장의 이미지나 비디오로 novel-view synthesi..
[논문] Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
·
Paper Review
https://github.com/IDEA-Research/Grounded-Segment-Anything GitHub - IDEA-Research/Grounded-Segment-Anything: Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable DiffusionGrounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything - IDEA-Research/Grounded-Segment-A...github.comAbstractO..
[논문] Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
·
Paper Review
https://github.com/IDEA-Research/GroundingDINO GitHub - IDEA-Research/GroundingDINO: [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Groun[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection" - IDEA-Research/GroundingDINOgithub.comhttps://arxiv.org/abs/2303.05499 Grounding DIN..
[Python] 백준 11559 - Puyo Puyo [Gold4]
·
Baekjoon
뿌요뿌요라는 게임을 들어보았을지 모르겠지만, 뿌요뿌요는 그림으로 봐도 알 수 있듯이 일본의 SEGA사에서 만든 게임이고 테트리스 처럼 여러 색깔과 모양의 블럭들이 내려와서 바닥이나 제일 위에 있는 블럭과 맞닿았을 때 그 상태에서 상하좌우로 4개의 같은 색깔의 모양이 위치하게 되면 그 블럭들이 터지면서 점수가 오르는 게임이다. 블럭이 터지게 되면 위에 있는 블럭들이 아래의 빈 공간을 메꾸기 위해 내려오게 되고 그 과정에서 새롭게 4개의 블럭이 생기면 연쇄적으로 터질 수 있다.따라서 이 문제에서도 이 게임의 방식과 동일하게 구현을 하면 된다.출처https://www.acmicpc.net/problem/11559풀이BFS를 이용하는데, 블럭이 모여서 터지게 되면 중력의 영향을 받아서 터진 블럭 위에 있는 블럭..
[논문] SAM: Segment Anything
·
Paper Review
https://arxiv.org/abs/2304.02643 Segment AnythingWe introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensearxiv.orgSegment Anything Segment AnythingMeta AI Computer Vision Researchsegment-anything.co..