{"list":"other","total":79,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"2312.00109","title":"Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering","created":"2023-11-30","cited_by_count":695},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393},{"id":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378},{"id":"2312.14937","title":"SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes","created":"2023-12-04","cited_by_count":347},{"id":"2303.14184","title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior","created":"2023-03-24","cited_by_count":343},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"id":"2312.00451","title":"FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting","created":"2023-12-01","cited_by_count":279},{"id":"2310.08529","title":"GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models","created":"2023-10-12","cited_by_count":255},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235},{"id":"2205.04978","title":"NeRF-Editing: Geometry Editing of Neural Radiance Fields","created":"2022-05-10","cited_by_count":217},{"id":"2304.06714","title":"Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction","created":"2023-04-13","cited_by_count":180},{"id":"2311.16037","title":"GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions","created":"2023-11-27","cited_by_count":168},{"id":"2312.00860","title":"Segment Any 3D Gaussians","created":"2023-12-01","cited_by_count":161},{"id":"2206.13597","title":"NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors","created":"2022-06-27","cited_by_count":125},{"id":"2403.08733","title":"GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing","created":"2024-03-13","cited_by_count":115},{"id":"2303.13277","title":"SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field","created":"2023-03-23","cited_by_count":94},{"id":"2404.18929","title":"DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing","created":"2024-04-29","cited_by_count":94},{"id":"2309.00616","title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","created":"2023-09-01","cited_by_count":82},{"id":"2310.03020","title":"Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models","created":"2023-10-04","cited_by_count":79},{"id":"2402.00864","title":"ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields","created":"2024-02-01","cited_by_count":68},{"id":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64},{"id":"2312.09168","title":"DiffusionLight: Light Probes for Free by Painting a Chrome Ball","created":"2023-12-14","cited_by_count":64},{"id":"2407.11793","title":"Click-Gaussian: Interactive Segmentation to Any 3D Gaussians","created":"2024-07-16","cited_by_count":58},{"id":"2409.08270","title":"FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally","created":"2024-09-12","cited_by_count":58},{"id":"2204.10850","title":"Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation","created":"2022-04-22","cited_by_count":57},{"id":"2410.19657","title":"DiffGS: Functional Gaussian Splatting Diffusion","created":"2024-10-25","cited_by_count":51},{"id":"2311.05461","title":"Control3D: Towards Controllable Text-to-3D Generation","created":"2023-11-09","cited_by_count":46},{"id":"2409.11356","title":"RenderWorld: World Model with Self-Supervised 3D Label","created":"2024-09-17","cited_by_count":46},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45},{"id":"2404.16666","title":"PhyRecon: Physically Plausible Neural Scene Reconstruction","created":"2024-04-25","cited_by_count":45},{"id":"2307.13908","title":"Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation","created":"2023-07-26","cited_by_count":39},{"id":"2312.06439","title":"DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior","created":"2023-12-11","cited_by_count":39},{"id":"2312.06655","title":"Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior","created":"2023-12-11","cited_by_count":32},{"id":"2209.05277","title":"StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints","created":"2022-09-12","cited_by_count":29},{"id":"2308.11974","title":"Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields","created":"2023-08-23","cited_by_count":28},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","cited_by_count":25},{"id":"2312.01663","title":"Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training","created":"2023-12-04","cited_by_count":21},{"id":"2312.09069","title":"PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion","created":"2023-12-14","cited_by_count":20},{"id":"2406.18462","title":"GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality","created":"2024-06-26","cited_by_count":18},{"id":"2403.10395","title":"Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding","created":"2024-03-15","cited_by_count":13},{"id":"2408.00083","title":"Localized Gaussian Splatting Editing with Contextual Awareness","created":"2024-07-31","cited_by_count":13},{"id":"2411.05006","title":"ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing","created":"2024-11-07","cited_by_count":12},{"id":"2407.10102","title":"3DEgo: 3D Editing on the Go!","created":"2024-07-14","cited_by_count":10},{"id":"2411.00850","title":"GWQ: Gradient-Aware Weight Quantization for Large Language Models","created":"2024-10-30","cited_by_count":8},{"id":"2312.02647","title":"TPA3D: Triplane Attention for Fast Text-to-3D Generation","created":"2023-12-05","cited_by_count":6},{"id":"2409.05310","title":"Neural Surface Reconstruction and Rendering for LiDAR-Visual Systems","created":"2024-09-09","cited_by_count":3}],"next_cursor":null}