diff --git a/survey.html b/survey.html index 41a5c07..590d575 100644 --- a/survey.html +++ b/survey.html @@ -1531,6 +1531,11 @@

See4D: Pose-Free 4D Generation via Auto-Regressive Inp const paperStore = { video: { A: [ + { title:"MIVIFI: Bridging Perspective and Fisheye Domains for Training Multi-View Fisheye Image Generation Models", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.23140", code:"#", project:"#"}, + { title:"SpatialCrafter: Single Image World Modeling with Generative 3D Proxies", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.27073", code:"#", project:"#"}, + { title:"4DStreamCtrl: Interactive Video Generation with Online 4D Control", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.25479", code:"#", project:"#"}, + { title:"ReWorld: An Interactive World Model with Long-Horizon Memory", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.23565", code:"#", project:"#"}, + { title:"NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.24212", code:"#", project:"#"}, { title:"MiniWorld: Democratizing the Training of Video World Models from Scratch", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.01127", code:"#", project:"#"}, { title:"RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.02953", code:"#", project:"#"}, { title:"muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.04412", code:"#", project:"#"}, @@ -1580,6 +1585,9 @@

See4D: Pose-Free 4D Generation via Auto-Regressive Inp { title:"DriveWeaver: Point-Conditioned Video Inpainting for Controllable Vehicle Insertion in Autonomous Driving Simulation", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2606.31918", code:"#", project:"#"}, ], B: [ + { title:"GeoWAM: Visual Geometry World Action Models for Autonomous Driving", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.23486", code:"#", project:"#"}, + { title:"4DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splatting", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.25956", code:"#", project:"#"}, + { title:"WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.26239", code:"#", project:"#"}, { title:"Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2607.11836", code:"#", project:"#"}, { title:"Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.06008", code:"#", project:"#"}, { title:"ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.14022", code:"#", project:"#"}, @@ -1613,6 +1621,10 @@

See4D: Pose-Free 4D Generation via Auto-Regressive Inp { title:"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2605.10564", code:"#", project:"#"}, ], C: [ + { title:"SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Rendering", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.17420", code:"#", project:"#"}, + { title:"4DSynth: Controllable Procedural World Synthesis for Dynamic Embodied Simulation", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.26947", code:"#", project:"#"}, + { title:"BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.22187", code:"#", project:"#"}, + { title:"CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.27406", code:"#", project:"#"}, { title:"From Pixels to States: Rethinking Interactive World Models as Game Engines", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2607.14076", code:"#", project:"#"}, { title:"Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2607.21594", code:"#", project:"#"}, { title:"Population-Scalable Multi-Agent World Modeling", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.08600", code:"#", project:"#"}, @@ -1646,6 +1658,12 @@

See4D: Pose-Free 4D Generation via Auto-Regressive Inp { title:"CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2607.07601", code:"#", project:"#"}, ], D: [ + { title:"Depth Anything V4: Dynamic 4D Scene Reconstruction via Riemannian Flow Matching on 4D Gaussian Splatting", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.18388", code:"#", project:"#"}, + { title:"UniQuery4R: Unified 4D Scene Reconstruction from a Single Query", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.17283", code:"#", project:"#"}, + { title:"SceneReGen: Generative Reconstruction of 3D Scenes from a Single Image", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.23930", code:"#", project:"#"}, + { title:"Gallileo-4D: Frozen Backbone Ensemble for Dynamic 4D Reconstruction", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.19743", code:"#", project:"#"}, + { title:"LagrangeGS: Non-Conservative Lagrangian System on Dynamic 3D Gaussian Splatting", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.22773", code:"#", project:"#"}, + { title:"VersaGauss: A Versatile Framework for Generating Multiphase Dynamics with 3D Gaussians", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.28069", code:"#", project:"#"}, { title:"3D Gaussian Splatting for Real-Time Radiance Field Rendering", authors:"", venue:"TOG", year:2023, paper:"https://arxiv.org/abs/2308.04079", code:"https://github.com/graphdeco-inria/gaussian-splatting", project:"https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/" }, { title:"Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", authors:"", venue:"ECCV", year:2024, paper:"https://arxiv.org/abs/2401.01339", code:"https://github.com/zju3dv/street_gaussians", project:"https://zju3dv.github.io/street_gaussians" }, { title:"Dynamic 3D Gaussian Fields for Urban Areas (4DGF)", authors:"", venue:"NeurIPS", year:2024, paper:"https://arxiv.org/abs/2406.03175", code:"https://github.com/tobiasfshr/map4d", project:"https://tobiasfshr.github.io/pub/4dgf/" }, @@ -1696,6 +1714,7 @@

See4D: Pose-Free 4D Generation via Auto-Regressive Inp }, occupancy: { A: [ + { title:"Generative Semantic Scene Completion", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.26737", code:"#", project:"#"}, { title:"GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.16234", code:"#", project:"#"}, { title:"Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data (SSD)", authors:"", venue:"arXiv", year:2023, paper:"https://arxiv.org/abs/2301.00527", code:"https://github.com/zoomin-lee/scene-scale-diffusion", project:"#"}, { title:"SemCity: Semantic Scene Generation with Triplane Diffusion", authors:"", venue:"CVPR", year:2024, paper:"https://arxiv.org/abs/2403.07773", code:"https://github.com/zoomin-lee/SemCity", project:"https://sglab.kaist.ac.kr/SemCity/"}, @@ -1772,6 +1791,7 @@

See4D: Pose-Free 4D Generation via Auto-Regressive Inp }, lidar: { A: [ + { title:"Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models", authors:"", venue:"arXiv", year:2026, paper:"https://arxiv.org/abs/2608.25418", code:"#", project:"#"}, { title:"DUSty: Learning to Drop Points for LiDAR Scan Synthesis", authors:"", venue:"IROS", year:2021, paper:"https://arxiv.org/abs/2102.11952", code:"https://github.com/kazuto1011/dusty-gan", project:"https://kazuto1011.github.io/dusty-gan/" }, { title:"LiDARGen: Learning to Generate Realistic LiDAR Point Clouds", authors:"", venue:"ECCV", year:2022, paper:"https://arxiv.org/abs/2209.03954", code:"https://github.com/vzyrianov/lidargen", project:"#"}, { title:"DUSty v2: Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data", authors:"", venue:"WACV", year:2023, paper:"https://arxiv.org/abs/2210.11750", code:"https://github.com/kazuto1011/dusty-gan-v2", project:"https://kazuto1011.github.io/dusty-gan-v2/"},