{"list":"other","total":85,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"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":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2012.03918","title":"NeRD: Neural Reflectance Decomposition from Image Collections","created":"2020-12-07","cited_by_count":449},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407},{"id":"2111.12503","title":"Extracting Triangular 3D Models, Materials, and Lighting From Images","created":"2021-11-24","cited_by_count":366},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"2104.00674","title":"PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting","created":"2021-04-01","cited_by_count":335},{"id":"2205.05198","title":"Reducing Activation Recomputation in Large Transformer Models","created":"2022-05-10","cited_by_count":302},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"2311.17977","title":"GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces","created":"2023-11-29","cited_by_count":252},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2309.14509","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","created":"2023-09-25","cited_by_count":245},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228},{"id":"2311.16473","title":"GS-IR: 3D Gaussian Splatting for Inverse Rendering","created":"2023-11-26","cited_by_count":224},{"id":"2502.06608","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","created":"2025-02-10","cited_by_count":213},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210},{"id":"2110.14373","title":"Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition","created":"2021-10-27","cited_by_count":205},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2303.05371","title":"3DGen: Triplane Latent Diffusion for Textured Mesh Generation","created":"2023-03-09","cited_by_count":183},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175},{"id":"2204.06837","title":"Modeling Indirect Illumination for Inverse Rendering","created":"2022-04-14","cited_by_count":168},{"id":"2304.12461","title":"TensoIR: Tensorial Inverse Rendering","created":"2023-04-24","cited_by_count":168},{"id":"2506.15442","title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","created":"2025-06-18","cited_by_count":165},{"id":"2206.03380","title":"Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising","created":"2022-06-07","cited_by_count":163},{"id":"2405.00666","title":"RGB$\\leftrightarrow$X: Image decomposition and synthesis using material- and lighting-aware diffusion models","created":"2024-05-01","cited_by_count":161},{"id":"2206.06360","title":"ARF: Artistic Radiance Fields","created":"2022-06-13","cited_by_count":147},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2405.14979","title":"CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner","created":"2024-05-23","cited_by_count":123},{"id":"1810.09718","title":"Single-Image SVBRDF Capture with a Rendering-Aware Deep Network","created":"2018-10-23","cited_by_count":116},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114},{"id":"2204.02232","title":"IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images","created":"2022-04-05","cited_by_count":111},{"id":"2505.17412","title":"Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention","created":"2025-05-23","cited_by_count":110},{"id":"2409.12957","title":"3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion","created":"2024-09-19","cited_by_count":101},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92},{"id":"2205.15768","title":"SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections","created":"2022-05-31","cited_by_count":89},{"id":"2505.14521","title":"Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling","created":"2025-05-20","cited_by_count":89},{"id":"2312.05133","title":"GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization","created":"2023-12-08","cited_by_count":87},{"id":"2505.07747","title":"Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets","created":"2025-05-12","cited_by_count":87},{"id":"1808.08601","title":"CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering","created":"2018-08-26","cited_by_count":85},{"id":"1804.05790","title":"Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image","created":"2018-04-16","cited_by_count":66},{"id":"2407.02445","title":"Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials","created":"2024-07-02","cited_by_count":66},{"id":"2003.12642","title":"Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images","created":"2020-03-27","cited_by_count":65},{"id":"2205.09343","title":"Physically-Based Editing of Indoor Scene Lighting from a Single Image","created":"2022-05-19","cited_by_count":62},{"id":"2405.07719","title":"USP: A Unified Sequence Parallelism Approach for Long Context Generative AI","created":"2024-05-13","cited_by_count":61},{"id":"2407.04699","title":"LaRa: Efficient Large-Baseline Radiance Fields","created":"2024-07-05","cited_by_count":55},{"id":"2512.08924","title":"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time","created":"2025-12-09","cited_by_count":54},{"id":"2311.12792","title":"Intrinsic Image Decomposition via Ordinal Shading","created":"2023-11-21","cited_by_count":53},{"id":"1809.00886","title":"Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks","created":"2018-09-04","cited_by_count":51},{"id":"2310.16044","title":"Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark","created":"2023-10-24","cited_by_count":51},{"id":"2412.03526","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos","created":"2024-12-04","cited_by_count":49},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49},{"id":"2304.13445","title":"Neural-PBIR Reconstruction of Shape, Material, and Illumination","created":"2023-04-26","cited_by_count":45},{"id":"2304.00782","title":"NeMF: Inverse Volume Rendering with Neural Microflake Field","created":"2023-04-03","cited_by_count":34},{"id":"1801.01075","title":"LIME: Live Intrinsic Material Estimation","created":"2018-01-03","cited_by_count":33},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29},{"id":"2410.06231","title":"RelitLRM: Generative Relightable Radiance for Large Reconstruction Models","created":"2024-10-08","cited_by_count":23},{"id":"2310.13030","title":"SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes","created":"2023-10-19","cited_by_count":19},{"id":"2401.09126","title":"Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting","created":"2024-01-17","cited_by_count":18},{"id":"2401.10171","title":"SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild","created":"2024-01-18","cited_by_count":18},{"id":"2504.20026","title":"LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields","created":"2025-04-28","cited_by_count":16},{"id":"2408.13055","title":"Atlas Gaussians Diffusion for 3D Generation","created":"2024-08-23","cited_by_count":15},{"id":"2506.09997","title":"DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos","created":"2025-06-11","cited_by_count":15},{"id":"2506.18890","title":"4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time","created":"2025-06-23","cited_by_count":14},{"id":"2503.08382","title":"Twinner: Shining Light on Digital Twins in a Few Snaps","created":"2025-03-11","cited_by_count":2}],"next_cursor":null}