{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"1801.07791","title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","created":"2018-01-23","cited_by_count":764},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2206.04670","title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","created":"2022-06-09","cited_by_count":436},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2311.16918","title":"RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D","created":"2023-11-28","cited_by_count":168},{"id":"2210.01055","title":"CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training","created":"2022-10-03","cited_by_count":160},{"id":"2306.03908","title":"SAM3D: Segment Anything in 3D Scenes","created":"2023-06-06","cited_by_count":157},{"id":"2402.11530","title":"Efficient Multimodal Learning from Data-centric Perspective","created":"2024-02-18","cited_by_count":122},{"id":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116},{"id":"2401.09419","title":"GARField: Group Anything with Radiance Fields","created":"2024-01-17","cited_by_count":109},{"id":"2103.14326","title":"Bidirectional Projection Network for Cross Dimension Scene Understanding","created":"2021-03-26","cited_by_count":95},{"id":"2312.11557","title":"SAI3D: Segment Any Instance in 3D Scenes","created":"2023-12-17","cited_by_count":90},{"id":"2312.02980","title":"GPT4Point: A Unified Framework for Point-Language Understanding and Generation","created":"2023-12-05","cited_by_count":71},{"id":"2304.04909","title":"SATR: Zero-Shot Semantic Segmentation of 3D Shapes","created":"2023-04-11","cited_by_count":62},{"id":"2312.03015","title":"PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation","created":"2023-12-05","cited_by_count":37},{"id":"2408.13679","title":"Segment Any Mesh","created":"2024-08-24","cited_by_count":37},{"id":"2303.09554","title":"PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision","created":"2023-03-16","cited_by_count":36},{"id":"2407.06191","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","created":"2024-07-08","cited_by_count":35},{"id":"2310.05107","title":"OV-PARTS: Towards Open-Vocabulary Part Segmentation","created":"2023-10-08","cited_by_count":31},{"id":"2312.04016","title":"PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation","created":"2023-12-07","cited_by_count":28},{"id":"2404.17569","title":"MaPa: Text-driven Photorealistic Material Painting for 3D Shapes","created":"2024-04-26","cited_by_count":27},{"id":"2407.13675","title":"MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis","created":"2024-07-18","cited_by_count":22},{"id":"2311.14262","title":"ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation","created":"2023-11-24","cited_by_count":18},{"id":"2312.03611","title":"DreamComposer: Controllable 3D Object Generation via Multi-View Conditions","created":"2023-12-06","cited_by_count":18},{"id":"2401.05906","title":"PartSTAD: 2D-to-3D Part Segmentation Task Adaptation","created":"2024-01-11","cited_by_count":18},{"id":"2303.14587","title":"PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters","created":"2023-03-25","cited_by_count":17},{"id":"2103.13030","title":"Learning Fine-Grained Segmentation of 3D Shapes without Part Labels","created":"2021-03-24","cited_by_count":14},{"id":"2405.00587","title":"GraCo: Granularity-Controllable Interactive Segmentation","created":"2024-05-01","cited_by_count":13},{"id":"2407.09648","title":"3x2: 3D Object Part Segmentation by 2D Semantic Correspondences","created":"2024-07-12","cited_by_count":10},{"id":"2404.02634","title":"3DStyleGLIP: Part-Tailored Text-Guided 3D Neural Stylization","created":"2024-04-03","cited_by_count":4}],"next_cursor":null}