mlsanityData to 7 Oct 2026

Sceniris: A Fast Procedural Scene Generation Framework

arXiv 2512.16896 ↗First posted 18 Dec 2025cs.RO cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

Synthetic 3D scenes are essential for developing Physical AI and generative models. Existing procedural generation methods often have low output throughput, creating a significant bottleneck in scaling up dataset creation. In this work, we introduce Sceniris, a highly efficient procedural scene generation framework for rapidly generating large-scale, collision-free scene variations. Sceniris also provides an optional robot reachability check, providing manipulation-feasible scenes for robot tasks. Sceniris is designed for maximum efficiency by addressing the primary performance limitations of the prior method, Scene Synthesizer. Leveraging batch sampling and faster collision checking in cuRobo, Sceniris achieves at least 234x speed-up over Scene Synthesizer. Sceniris also expands the object-wise spatial relationships available in prior work to support diverse scene requirements. Our code is available at https://github.com/rai-inst/sceniris

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 56 of its 71 references that are in the map. First posted on arXiv 18 Dec 2025.

Builds on

56 of 71 references.

References · 56

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  8. 2023Qwen Technical Reportcited by 3,273
  9. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  10. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  11. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  12. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
38 more
  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  2. 2025DINOv3cited by 1,297
  3. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  4. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  5. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  6. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  7. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  8. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  9. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  10. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  11. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  12. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  13. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  14. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  15. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  16. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 403
  17. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  18. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  19. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  20. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  21. 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 206
  22. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  23. 2023AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into Onecited by 165
  24. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 142
  25. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 122
  26. 2023GenSim: Generating Robotic Simulation Tasks via Large Language Modelscited by 120
  27. 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusioncited by 109
  28. 2024Automated Creation of Digital Cousins for Robust Policy Learningcited by 88
  29. 2024RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Modelscited by 88
  30. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  31. 2024DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Samplingcited by 72
  32. 2023ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenescited by 68
  33. 2024RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)cited by 68
  34. 2024Theia: Distilling Diverse Vision Foundation Models for Robot Learningcited by 56
  35. 2024GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMscited by 48
  36. 2025RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learningcited by 48
  37. 2023cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generationcited by 46
  38. 2024SceneTeller: Language-to-3D Scene Generationcited by 43

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.