[Arxiv 2024] InstantSplat 리뷰
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds (arXiv, 2024)
Paper Review
[Arxiv 2024] Inter-pose 요약
Can Generative Video Models Help Pose Estimation? (Inter-pose)
[ECCV 2024] D-SCo paper review
D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
[ECCV 2024] HORSE paper review
HORSE: 3D Reconstruction of Objects in Hands without Real World 3D Supervision
[CVPR 2024] HUGS paper review
HUGS: Human Gaussian Splats
[CVPR 2024][Highlight] HOLD paper review
HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video
[arXiv preprint] Shape of Motion paper review
Shape of Motion: 4D Reconstruction from a Single Video
[3DV 2021] Dance In the Wild 논문 리뷰
Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis
[CVPR 2024] InterHandGen 논문 리뷰
InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion
[ECCV 2022] The One Where They Reconstructed 3D Humans and Environments in TV shows 논문 리뷰
Sitcom3D: The One Where They Reconstructed 3D Humans and Environments in TV shows
[CVPR 2022] Human Mesh Recovery from Multiple Shots 논문 리뷰
multishot: Human Mesh Recovery from Multiple Shots
[CVPR 2024] SpatialVLM 논문 리뷰
Spatial VLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
[CVPR 2022] CoCoOp 논문 리뷰
CoCoOp: Conditional Prompt Learning for Vision-Language Models
[IJCV 2022] CoOp 논문 리뷰
CoOp: Learning to Prompt for Vision-Language Models
[CVPR 2021] CLIP 논문 리뷰
CLIP: Learning Transferable Visual Models From Natural Language Supervision
[CVPR 2021] Mesh Transformer 논문 리뷰
METRO: End-to-End Human Pose and Mesh Reconstruction with Transformers
[CVPR 2020] VIBE 논문 리뷰
VIBE: Video Inference for Human Body Pose and Shape Estimation
[ICLR 2021] Deformable DETR 논문 리뷰
Deformable DETR: Deformable Transfomers for End-to-End Object Detection
[CVPR 2022] Implementation of DINO
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
[CVPR 2022] DINO 논문 리뷰
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection