Copyright © China3DV 2025 中国三维视觉大会 京ICP备2022017585号-2
| 页面序号 | 论文题目 | 会议/期刊 | 主讲人 | 单位 |
|---|---|---|---|---|
| 1 | DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input | AAAI 2025 | 田旗舰 | 上交 |
| 5 | CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians | ICLR 2025 | 刘洋 | 中科院自动化所 |
| 9 | AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction | ICLR 2025 | 高景南 | 上交 |
| 13 | BWFormer: Building Wireframe Reconstruction from airborne LiDAR point clouds with Transformer | CVPR 2025 | 刘昱州 | 中科院自动化所 |
| 15 | SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos | CVPR 2025 | 刘宇政 | 北大 |
| 16 | NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields | ICLR 2025 | 叶翰樵 | 国科大 |
| 20 | NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation | CVPR 2025 | 陈梓怡 | 高德地图 |
| 26 | 3D-SLNR: A Super Lightweight Neural Representation for Large-scale 3D Mapping | CVPR 2025 | 师晨辉 | 中科院自动化所 |
| 28 | Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation | CVPR 2025 | 林浩通 | 浙大 |
| 38 | Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis | CVPR 2025 | 黄江勇 | 北大 |
| 41 | High-Fidelity Lightweight Mesh Reconstruction from Point Clouds | CVPR 2025 | 张琛 | 华科 |
| 46 | MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image | CVPR 2025 | 李绍铭 | 中国海大 |
| 50 | FreeTimeGS: Free Gaussians at Anytime Anywhere for Dynamic Scene Reconstruction | CVPR 2025 | 王一凡 | 浙大 |
| 62 | Unlocking Generalization Power in LiDAR Point Cloud Registration | CVPR 2025 | 曾振轩 | 西工大 |
| 66 | DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery | CVPR 2025 | 唐家栋 | 北理工 |
| 67 | OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging | CVPR 2025 | 唐熠杰 | 国防科大 |
| 69 | Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues | CVPR 2025 | 欧亮汛 | 港大 |
| 70 | Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations | 投稿中 | 蔡棽 | 东华 |
| 73 | Hierarchical Point Saliency for 3D Keypoint Detection | TVCG | 阳诚砖 | 浙师大 |
| 81 | SSR-2D: Semantic 3D Scene Reconstruction from 2D Images | TPAMI | 智帅峰 | 国防科大 |
| 87 | DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis | CVPR 2025 | 曾子寅 | 武大 |
| 90 | MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision | CVPR 2025 | 王瑞程 | 中科大 |
| 页面序号 | 论文题目 | 会议/期刊 | 主讲人 | 单位 |
|---|---|---|---|---|
| 2 | AdaDPCC: Adaptive Rate Control and Rate-Distortion-Complexity Optimization for Dynamic Point Cloud Compression | AAAI 2025 | 高伟 | 北大 |
| 3 | UniPCGC: Towards Practical Point Cloud Geometry Compression via An Efficient Unified Approach | AAAI 2025 | 高伟 | 北大 |
| 4 | Point Cloud Semantic Segmentation With Sparse and Inhomogeneous Annotations | AAAI 2025 | 高伟 | 北大 |
| 8 | Shape as Line Segments: Accurate and Flexible Implicit Surface Representation | ICLR 2025 | 任思宇 | 港城大 |
| 18 | Deformable Radial Kernel Splatting | CVPR 2025 | 黄熠华 | 港大 |
| 19 | EnvGS: Modeling View-Dependent Appearance with Environment Gaussian | CVPR 2025 | 谢涛 | 浙大 |
| 23 | SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network | AAAI 2025 | 聂子铭 | 西工大 |
| 29 | High-quality Point Cloud Oriented Normal Estimation via Hybrid Angular and Euclidean Distance Encoding | CVPR 2025 | 李元琪 | 南大 |
| 30 | ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting | CVPR 2025 | 郭俊甫 | 中科大 |
| 32 | MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining | CVPR 2025 | 刘昀泽 | 清华 |
| 36 | 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion | CVPR 2025 | 陈昭熹 | NTU |
| 45 | Structured 3D Latents for Scalable and Versatile 3D Generation | CVPR 2025 | 向剑锋 | 清华 |
| 47 | Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting | ICLR 2025 | 刘宇 | 清华 |
| 51 | Mitigating Ambiguities in 3D Classification with Gaussian Splatting | CVPR 2025 | 张瑞祺 | 南大 |
| 55 | MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation | CVPR 2025 | 黄泽桓 | 北航 |
| 59 | Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation | CVPR 2025 | 林坚涛, 杨鑫 | 港科大(广州),港科大 |
| 68 | Decompositional Neural Scene Reconstruction with Generation Diffusion Prior | CVPR 2025 | 倪俊锋 | 清华 |
| 71 | RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting | CVPR 2025 | 戴启宇 | 北大 |
| 89 | FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views | CVPR 2025 | 徐英豪 | Stanford University |
| 91 | TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting | CVPR 2025 | 熊伯君 | 北大 |
| 页面序号 | 论文题目 | 会议/期刊 | 主讲人 | 单位 |
|---|---|---|---|---|
| 6 | L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection | AAAI 2025 | 黄勋 | 厦大 |
| 17 | Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization | CVPR 2025 | 待定 | 港大 或 Apple |
| 27 | ET-SEED: EFFICIENT TRAJECTORY-LEVEL SE(3) EQUIVARIANT DIFFUSION POLICY | ICLR 2025 | 陈越 | 北大 |
| 33 | FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenes | CVPR 2025 | 范略 | 中科院自动化所 |
| 34 | VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion | AAAI 2025 | 王萌 | 湖南大学 |
| 35 | MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection | ICLR 2024 | 杨禹雪 | 中科院自动化所 |
| 37 | LightLoc: Learning Outdoor LiDAR Localization at Light Speed | CVPR 2025 | 李文 | 厦大 |
| 42 | SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts | CVPR 2025 | 赵世佳 | 厦大 |
| 43 | Learning to Detect Objects from Multi-AgentLiDAR Scans without Manual Labels | CVPR 2025 | 夏启明 | 厦大 |
| 49 | LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation | CVPR 2025 | 周晨旭 | 浙大 |
| 53 | Text to Point Cloud Localization with Multi-Level Negative Contrastive Learning | AAAI 2025 | 刘敦强 | 厦大 |
| 56 | DiffLC: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement | CVPR 2025 | 黄泳树 | 厦大 |
| 61 | EgoLM: Multi-Modal Language Model of Egocentric Motions | CVPR 2025 | 洪方舟 | NTU |
| 63 | ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate | CVPR 2025 | 颜明 | 厦大 |
| 65 | TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization | CVPR 2025 | 王文佳 | 港大 |
| 72 | V-HOP: Visuo-Haptic 6D Object Pose Tracking | 投稿中 | 李鸿宇 | Brown University |
| 76 | TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation | CVPR 2025 | 赵泓翔 | 港中文 (深圳) |
| 83 | SkillMimic: Learning Reusable Basketball Skills from Demonstrations | CVPR 2025 | 喻润一 | 港科大 |
| 84 | ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion | 投稿中 | 张家珺 | 北邮 |
| 88 | GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation | CVPR 2025 | 吴睿海 | 北大 |
| 92 | Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations | SIGGRAPH (Conditional accept) | 王萌槐 | 港科大 |
| 页面序号 | 论文题目 | 会议/期刊 | 主讲人 | 单位 |
|---|---|---|---|---|
| 7 | CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks | AAAI 2025 | 丁阳 | 北信科 |
| 10 | HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset | CVPR 2025 | 储泽栋 | 高德地图 |
| 11 | AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer | CVPR 2025 | 吕劲 | 南科大 |
| 12 | ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model | CVPR 2025 | 路舜麟 | 港中文(深圳),上海 Al Lab |
| 22 | EasyHOL: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild | CVPR 2025 | 刘雨萌 | 港大,上科大 |
| 24 | CORF4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object Rearrangement | CVPR 2025 | 刘昀 | 清华 |
| 25 | IDOL: Instant Photorealistic 3D Human Creation from a Single Image | CVPR 2025 | 庄义昱 | 南大 |
| 31 | DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References | ICLR 2025 | 刘雪怡 | 清华 |
| 39 | DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations | CVPR 2025 | 彭子乔 | 人大 |
| 40 | Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture | CVPR 2025 | 李炫辰 | 上交 |
| 48 | Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning | CVPR 2025 | 黄步真 | 东南 |
| 57 | MagicArticulate: Make Your 3D Models Articulation-Ready | CVPR 2025 | 宋超越 | NTU |
| 58 | TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting | CVPR 2025 | 陈建川 | 阿里巴巴 |
| 60 | InsTaG: Learning Personalized 3D Talking Head from Few-Second Video | CVPR 2025 | 李嘉禾 | 北航 |
| 74 | Interactive humanoid: Online full-body motion reaction synthesis with social affordance canonicalization and forecasting | 3DV 2025 | 刘昀泽 | 清华 |
| 77 | X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention | ICLR 2025 | 赵笑晨 | 清华 |
| 79 | GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor | 3DV 2025 | Xiangyue Liu | 港科大 |
| 80 | GBC-Splat: Generalizable Gaussian-Based Clothed Human Digitalization under Sparse RGB Cameras | CVPR 2025 | 涂汉璋 | 清华 |
| 82 | FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis | ECCV 2024 | 樊珂 | 上交 |
| 85 | Audio Matters Tool Enhancing Markerless Motion Capture with Audio Signals for String Performance Capture. | ACM SIGGRAPH 2024 & TOG | 丘治平 | 央音 |
| 86 | HHAvatar: Gaussian Head Avatar with Dynamic Hairs | 投稿中 | 廖展锋 | 清华 |
| 93 | LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds | 投稿中 | 邱陵腾 | 阿里通义实验室 |
| 95 | Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting | CVPR 2025 | Hanxi Liu | 北大 |
| 页面序号 | 论文题目 | 会议/期刊 | 主讲人 | 单位 |
|---|---|---|---|---|
| 14 | MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model | CVPR 2025 | Chaohui Yu | 阿里巴巴 |
| 21 | Attention Distillation: A Unified Approach to Visual Characteristics Transfer | CVPR 2025 | 高旭 | 深大 |
| 44 | StageDesigner: Artistic Stage Generation for Scenography via Theater Scripts | CVPR 2025 | 甘照星 | 复旦 |
| 52 | StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation | CVPR 2025 | 叶智超 | 商汤 |
| 54 | FilmComposer: LLM-Driven Music Production for Silent Film Clips | CVPR 2025 | 何其乐 | 上大 |
| 64 | ImViD: Immersive Volumetric Videos for Enhanced VR Engagement | CVPR 2025 | 杨正贤 | 清华 |
| 75 | SketchVideo: Sketch-based Video Generation and Editing | CVPR 2025 | 刘锋林 | 中科院计算所 |
| 78 | ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping | CVPR 2025 | 庞有鑫 | 清华 |
| 94 | Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models | NeurIPS 2024 | 尹雨阳 | 北交 |
