CVPR 2024 最佳论文候选（翻译+解读共建）

输入“/”快速插入内容

CVPR 2024 最佳论文候选（翻译+解读共建）

用户1672

用户2268

用户5190

2024年6月6日修改

CVPR 2024 最佳论文候选（翻译+解读共建）知识库共建招募

common.docs_name - LarkCCM_Docs_Menu_Image

注意事项：千万不能抄袭，图片copy需要标注引用来源～

相关主题	论文		领取地址	最终撰写地址	领取人
视觉与图形	Objects as Volumes: A Stochastic Geometry View of Opaque Solids	https://arxiv.org/abs/2312.15406v2	CVPR001	CVPR001 Objects as Volumes: A Stochastic Geometry View of Opaque Solids
单视图 3D	Repurposing Diffusion-Based lmage Generators for Monocular Depth Estimation	https://arxiv.org/abs/2312.02145	CVPR002	CVPR002 Repurposing Diffusion-Based lmage Generators for Monocular Depth Estimation
视觉，语言，推理	Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods	https://arxiv.org/abs/2212.06872	CVPR003	CVPR003 Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods
	MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI	https://arxiv.org/abs/2311.16502	CVPR004	CVPR004 MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
基于医学和物理学的视觉	EventPS. Real-Time Photometric Stereo Using an Event Camera	https://drive.google.com/file/d/1JU9tn4mgXSjuHaN6TfD8H8G0sSFUEmRY/view?usp=sharing	CVPR005	CVPR005 EventPS. Real-Time Photometric Stereo Using an Event Camera
	MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation	https://github.com/dengxl0520/MemSAM	CVPR006	CVPR006 MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation
	Correlation-aware Coarse-to-fine MLPs for Deformable Medical lmage Registration	https://github.com/MungoMeng/Registration-CorrMLP	CVPR007	CVPR007 Correlation-aware Coarse-to-fine MLPs for Deformable Medical lmage Registration
自主导航和自我中心视觉	Producing and Leveraging Online Map Uncertainty in Trajectory Prediction	https://arxiv.org/abs/2403.16439	CVPR008	CVPR008 Producing and Leveraging Online Map Uncertainty in Trajectory Prediction
3D	SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency	https://github.com/paul0noah/spider-match	CVPR009	CVPR009 SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency
	PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness	https://arxiv.org/abs/2312.02158	CVPR010	CVPR010 PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness
	PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two- Bounce Lidar	https://arxiv.org/abs/2312.14239	CVPR011	CVPR011 PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two- Bounce Lidar
行动和动作	Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation	https://arxiv.org/abs/2404.01518	CVPR012	CVPR012 Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation
数据和评估	Rich Human Feedback for Text-to-lmage Generation	https://arxiv.org/abs/2312.10240	CVPR013	CVPR013 Rich Human Feedback for Text-to-lmage Generation
	BioCLlP: A Vision Foundation Model for the Tree of Life	https://arxiv.org/abs/2311.18803	CVPR014	CVPR014 BioCLlP: A Vision Foundation Model for the Tree of Life
多视角和传感器融合 3D	Grounding and Enhancing Grid-based Models for Neural Fields	https://arxiv.org/abs/2403.20002	CVPR015	CVPR015 Grounding and Enhancing Grid-based Models for Neural Fields
	NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Seqmentation	http://cnhaox.com/NeRF-HuGS/	CVPR016	CVPR016 NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Seqmentation
	Mip-Splatting: Alias-free 3D Gaussian Splatting	https://github.com/autonomousvision/mip-splatting	CVPR017	CVPR017 Mip-Splatting: Alias-free 3D Gaussian Splatting
	pixelSplat. 3D Gaussian Splats from lmage Pairs for Scalable Generalizable 3D Reconstruction	https://davidcharatan.com/pixelsplat/	CVPR018